PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2303.05470공식 코드 · Papers with Code

Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases

The problem of spurious correlations (SCs) arises when a classifier relies on non-predictive features that happen to be correlated with the labels in the training data. For example, a classifier may misclassify dog breeds based on the background of dog images. This happens when the backgrounds are correlated with other breeds in the training data, leading to misclassifications during test time. Previous SC benchmark datasets suffer from varying issues, e.g., over-saturation or only containing one-to-one (O2O) SCs, but no many-to-many (M2M) SCs arising between groups of spurious attributes and classes. In this paper, we present \benchmark-\{O2O, M2M\}-\{Easy, Medium, Hard\}, an image classification benchmark suite containing spurious correlations between classes and backgrounds. To create this dataset, we employ a text-to-image model to generate photo-realistic images and an image captioning model to filter out unsuitable ones. The resulting dataset is of high quality and contains approximately 152k images. Our experimental results demonstrate that state-of-the-art group robustness methods struggle with \benchmark, most notably on the Hard-splits with none of them getting over $70\%$ accuracy on the hardest split using a ResNet50 pretrained on ImageNet. By examining model misclassifications, we detect reliances on spurious backgrounds, demonstrating that our dataset provides a significant challenge.

arXiv:2401.05570

Siamese Networks with Soft Labels for Unsupervised Lesion Detection and Patch Pretraining on Screening Mammograms

Self-supervised learning has become a popular way to pretrain a deep learning model and then transfer it to perform downstream tasks. However, most of these methods are developed on large-scale image datasets that contain natural objects with clear textures, outlines, and distinct color contrasts. It remains uncertain whether these methods are equally effective for medical imaging, where the regions of interest often blend subtly and indistinctly with the surrounding tissues. In this study, we propose an alternative method that uses contralateral mammograms to train a neural network to encode similar embeddings when a pair contains both normal images and different embeddings when a pair contains normal and abnormal images. Our approach leverages the natural symmetry of human body as weak labels to learn to distinguish abnormal lesions from background tissues in a fully unsupervised manner. Our findings suggest that it's feasible by incorporating soft labels derived from the Euclidean distances between the embeddings of the image pairs into the Siamese network loss. Our method demonstrates superior performance in mammogram patch classification compared to existing self-supervised learning methods. This approach not only leverages a vast amount of image data effectively but also minimizes reliance on costly labels, a significant advantage particularly in the field of medical imaging.

arXiv:2402.13465

Unsupervised learning based object detection using Contrastive Learning

Training image-based object detectors presents formidable challenges, as it entails not only the complexities of object detection but also the added intricacies of precisely localizing objects within potentially diverse and noisy environments. However, the collection of imagery itself can often be straightforward; for instance, cameras mounted in vehicles can effortlessly capture vast amounts of data in various real-world scenarios. In light of this, we introduce a groundbreaking method for training single-stage object detectors through unsupervised/self-supervised learning. Our state-of-the-art approach has the potential to revolutionize the labeling process, substantially reducing the time and cost associated with manual annotation. Furthermore, it paves the way for previously unattainable research opportunities, particularly for large, diverse, and challenging datasets lacking extensive labels. In contrast to prevalent unsupervised learning methods that primarily target classification tasks, our approach takes on the unique challenge of object detection. We pioneer the concept of intra-image contrastive learning alongside inter-image counterparts, enabling the acquisition of crucial location information essential for object detection. The method adeptly learns and represents this location information, yielding informative heatmaps. Our results showcase an outstanding accuracy of \textbf{89.2\%}, marking a significant breakthrough of approximately \textbf{15x} over random initialization in the realm of unsupervised object detection within the field of computer vision.

arXiv:2503.19223공식 코드 · Papers with Code

Face Spoofing Detection using Deep Learning

Digital image spoofing has emerged as a significant security threat in biometric authentication systems, particularly those relying on facial recognition. This study evaluates the performance of three vision based models, MobileNetV2, ResNET50, and Vision Transformer, ViT, for spoof detection in image classification, utilizing a dataset of 150,986 images divided into training , 140,002, testing, 10,984, and validation ,39,574, sets. Spoof detection is critical for enhancing the security of image recognition systems, and this research compares the models effectiveness through accuracy, precision, recall, and F1 score metrics. Results reveal that MobileNetV2 outperforms other architectures on the test dataset, achieving an accuracy of 91.59%, precision of 91.72%, recall of 91.59%, and F1 score of 91.58%, compared to ViT 86.54%, 88.28%, 86.54%, and 86.39%, respectively. On the validation dataset, MobileNetV2, and ViT excel, with MobileNetV2 slightly ahead at 97.17% accuracy versus ViT 96.36%. MobileNetV2 demonstrates faster convergence during training and superior generalization to unseen data, despite both models showing signs of overfitting. These findings highlight MobileNetV2 balanced performance and robustness, making it the preferred choice for spoof detection applications where reliability on new data is essential. The study underscores the importance of model selection in security sensitive contexts and suggests MobileNetV2 as a practical solution for real world deployment.

arXiv:2504.14798v2cs.LG

RUB: 언러닝된 모델 내 잔여 지식 평가

RUB: Evaluating Residual Knowledge in Unlearned Models

머신 언러닝(MUL)은 프라이버시 보호와 콘텐츠 규제를 위한 핵심 메커니즘으로 떠올랐으나, 현재 기술들은 민감한 정보의 완전한 제거를 보장하는 데 종종 실패합니다. 대부분의 기존 연구는 언러닝의 수행 여부 검증에 집중하지만, 모델이 잊혀진 지식을 복구하려는 적대적 시도에 대해 강건한지라는 중요한 문제를 간과하고 있습니다. 본 연구에서는 모델이 재학습된 모델과 구별할 수 없으면서도 다양한 적대적 위협에 대해 내성을 가질 것을 요구하는 강건한 언러닝(Robust Unlearning) 원칙을 제안합니다. 이 원칙을 구체화하기 위해, 분류, 이미지-투-이미지 복원, 텍스트-투-이미지 합성에 걸쳐 언러닝 알고리즘의 강건성을 체계적으로 평가하는 통합 벤치마크인 RUB(Robust Unlearning Benchmark)를 제안합니다. 이 프레임워크 내에서 잔여 정보를 탐지하기 위한 일반화 가능한 방법으로 언러닝 매핑 공격(Unlearning Mapping Attack, UMA)을 소개하고, 기존 공격 전략들이 일반적인 UMA 프레임워크를 준수하는 한 이 프레임워크 내로 적응될 수 있음을 보여줍니다. 판별 및 생성 작업에 걸친 실험을 통해 최첨단 언러닝 방법들이 표준 검증 메트릭을 통과하더라도 이러한 평가 하에서는 여전히 취약함을 확인했습니다. 강건성을 핵심 기준으로 삼고 적대적 평가를 위한 벤치마크를 제공함으로써, RUB가 더 신뢰할 수 있고 안전한 언러닝 관행으로 나아가는 길을 열기를 희망합니다. RUB의 코드베이스와 모델 체크포인트는 공개될 예정입니다.

arXiv:2506.08849공식 코드 · Papers with Code

Adapting Vision-Language Foundation Model for Next Generation Medical Ultrasound Image Analysis

Medical ultrasonography is an essential imaging technique for examining superficial organs and tissues, including lymph nodes, breast, and thyroid. It employs high-frequency ultrasound waves to generate detailed images of the internal structures of the human body. However, manually contouring regions of interest in these images is a labor-intensive task that demands expertise and often results in inconsistent interpretations among individuals. Vision-language foundation models, which have excelled in various computer vision applications, present new opportunities for enhancing ultrasound image analysis. Yet, their performance is hindered by the significant differences between natural and medical imaging domains. This research seeks to overcome these challenges by developing domain adaptation methods for vision-language foundation models. In this study, we explore the fine-tuning pipeline for vision-language foundation models by utilizing large language model as text refiner with special-designed adaptation strategies and task-driven heads. Our approach has been extensively evaluated on six ultrasound datasets and two tasks: segmentation and classification. The experimental results show that our method can effectively improve the performance of vision-language foundation models for ultrasound image analysis, and outperform the existing state-of-the-art vision-language and pure foundation models. The source code of this study is available at \href{https://github.com/jinggqu/NextGen-UIA}{GitHub}.

arXiv:2205.07075

Corrosion Detection for Industrial Objects: From Multi-Sensor System to 5D Feature Space

Corrosion is a form of damage that often appears on the surface of metal-made objects used in industrial applications. Those damages can be critical depending on the purpose of the used object. Optical-based testing systems provide a form of non-contact data acquisition, where the acquired data can then be used to analyse the surface of an object. In the field of industrial image processing, this is called surface inspection. We provide a testing setup consisting of a rotary table which rotates the object by 360 degrees, as well as industrial RGB cameras and laser triangulation sensors for the acquisition of 2D and 3D data as our multi-sensor system. These sensors acquire data while the object to be tested takes a full rotation. Further on, data augmentation is applied to prepare new data or enhance already acquired data. In order to evaluate the impact of a laser triangulation sensor for corrosion detection, one challenge is to at first fuse the data of both domains. After the data fusion process, 5 different channels can be utilized to create a 5D feature space. Besides the red, green and blue channels of the image (1-3), additional range data from the laser triangulation sensor is incorporated (4). As a fifth channel, said sensor provides additional intensity data (5). With a multi-channel image classification, a 5D feature space will lead to slightly superior results opposed to a 3D feature space, composed of only the RGB channels of the image.

arXiv:2403.16499

Self-Supervised Learning for Medical Image Data with Anatomy-Oriented Imaging Planes

Self-supervised learning has emerged as a powerful tool for pretraining deep networks on unlabeled data, prior to transfer learning of target tasks with limited annotation. The relevance between the pretraining pretext and target tasks is crucial to the success of transfer learning. Various pretext tasks have been proposed to utilize properties of medical image data (e.g., three dimensionality), which are more relevant to medical image analysis than generic ones for natural images. However, previous work rarely paid attention to data with anatomy-oriented imaging planes, e.g., standard cardiac magnetic resonance imaging views. As these imaging planes are defined according to the anatomy of the imaged organ, pretext tasks effectively exploiting this information can pretrain the networks to gain knowledge on the organ of interest. In this work, we propose two complementary pretext tasks for this group of medical image data based on the spatial relationship of the imaging planes. The first is to learn the relative orientation between the imaging planes and implemented as regressing their intersecting lines. The second exploits parallel imaging planes to regress their relative slice locations within a stack. Both pretext tasks are conceptually straightforward and easy to implement, and can be combined in multitask learning for better representation learning. Thorough experiments on two anatomical structures (heart and knee) and representative target tasks (semantic segmentation and classification) demonstrate that the proposed pretext tasks are effective in pretraining deep networks for remarkably boosted performance on the target tasks, and superior to other recent approaches.

arXiv:2407.14570

Are handcrafted filters helpful for attributing AI-generated images?

Recently, a vast number of image generation models have been proposed, which raises concerns regarding the misuse of these artificial intelligence (AI) techniques for generating fake images. To attribute the AI-generated images, existing schemes usually design and train deep neural networks (DNNs) to learn the model fingerprints, which usually requires a large amount of data for effective learning. In this paper, we aim to answer the following two questions for AI-generated image attribution, 1) is it possible to design useful handcrafted filters to facilitate the fingerprint learning? and 2) how we could reduce the amount of training data after we incorporate the handcrafted filters? We first propose a set of Multi-Directional High-Pass Filters (MHFs) which are capable to extract the subtle fingerprints from various directions. Then, we propose a Directional Enhanced Feature Learning network (DEFL) to take both the MHFs and randomly-initialized filters into consideration. The output of the DEFL is fused with the semantic features to produce a compact fingerprint. To make the compact fingerprint discriminative among different models, we propose a Dual-Margin Contrastive (DMC) loss to tune our DEFL. Finally, we propose a reference based fingerprint classification scheme for image attribution. Experimental results demonstrate that it is indeed helpful to use our MHFs for attributing the AI-generated images. The performance of our proposed method is significantly better than the state-of-the-art for both the closed-set and open-set image attribution, where only a small amount of images are required for training.

논문 ID: 2024.11055

Ta-Adapter: Enhancing few-shot CLIP with task-aware encoders

Contrastive Language-Image Pre-training (CLIP) has shown impressive zero-shot transfer capabilities, but its potential for specific downstream tasks is not fully utilized. To further enhance CLIP’s few-shot capability for specific datasets, some subsequent works have been proposed, such as methods based on lightweight adapters and prompt learning. However, since CLIP is pretrained on a diverse collection of image and text pairs sourced from the internet, it is difficult to sufficiently tune models to specific datasets using only lightweight adaptions. In this paper, we argue that largely modifying the internal representations within CLIP’s encoders can yield better results on downstream datasets. In this work, we introduce Ta-Adapter, a method that equips both the visual and textual encoders of CLIP with task-specific prompts. These prompts are generated using a collaborative prompt learning approach, which allows the encoders to produce representations that are better aligned with specific downstream datasets. Then, we initialize an adapter module using the optimized features generated by the task-aware visual encoder for further feature alignment, and this module can also be further fine-tuned. Our extensive experiments on image classification datasets show that compared to the state-of-theart few-shot methods Tip-Adapter-F and MaPLe, our model exhibits good performance and obtains an average absolute gain of 2.04% and 1.62% on 11 different image recognition datasets, respectively. In conclusion, this work presents a unique and effective approach to unlocking the full potential of CLIP’s few-shot learning capabilities.

arXiv:2606.22089v1cs.CV

BAC-JEPA: 합성 유방촬영 영상 유도 감독을 통한 라벨 효율적 유방 동맥 석회화 분할

BAC-JEPA: Label-Efficient Breast Arterial Calcification Segmentation via Synthetic Mammography-Guided Supervision

유방촬영 검사(screening mammograms)에서의 유방 동맥 석회화(BAC)는 새롭게 부상하는 심혈관 위험 바이오마커이지만, 정량적 활용에는 재현 가능한 분할이 필요하고 전문가의 픽셀 수준 라벨은 비용이 큽니다. 본 논문은 BAC-JEPA를 제시합니다. 이는 정확한 마스크와 함께 실제 유방촬영 배경에 절차적으로 생성된 동맥 석회화를 삽입한 데이터로 학습한 라벨 효율적 분할 프레임워크입니다. 후보 배경은 예측 BAC 반응이 낮은 모델 스크리닝 유방촬영 영상에서 선별되었으며, 생성기는 동맥 구조, 질병 부담, 방사선학적 소견, 비동맥성 석회화와 금속 물체를 포함한 hard-negative 방해 요소를 샘플링합니다. 합성 마스크는 유방촬영 자기지도 Vision Transformer 인코더와 고해상도 컨벌루션 디코더와 결합하여 전체 해상도 분할 맵을 생성합니다. 본 연구는 34,956명 환자의 75,472건 유방촬영 검사를 배경 선별 및 표현 학습에 사용하고, 10,000개 배경에서 생성한 합성 이미지로 학습하여, 1,000개 개발 배경으로 체크포인트를 선별했으며, 사람이 라벨링한 BacSeg 합성 2D 유방촬영 1,000건 전체에서 전이를 평가했습니다. 보류된 합성 검증 데이터에서 더 큰 백본은 IoU 0.5325, Dice 0.6357을 달성했습니다. BacSeg에서는 분할 확률 맵으로부터의 이미지 수준 분류가 AUROC 0.8719를 달성했고, 더 작은 백본은 0.8547을 기록했습니다. 4뷰 추론은 RTX 5090 GPU에서 110.68--213.63 ms가 소요되었고, severe-preset 합성 이미지 생성은 멀티코어 워크스테이션에서 이미지당 평균 2.7071 s였습니다. 이러한 결과는 BAC 특화 합성 감독이 인간의 픽셀 수준 학습 마스크 없이도 유용한 이미지 수준 전이를 달성할 수 있음을 보여주며, 전문가 검토 실제 유방촬영 분할은 임상 검증 및 보정을 위해 여전히 필요합니다.

arXiv:2008.02840

Assisted Perception: Optimizing Observations to Communicate State

We aim to help users estimate the state of the world in tasks like robotic teleoperation and navigation with visual impairments, where users may have systematic biases that lead to suboptimal behavior: they might struggle to process observations from multiple sensors simultaneously, receive delayed observations, or overestimate distances to obstacles. While we cannot directly change the user's internal beliefs or their internal state estimation process, our insight is that we can still assist them by modifying the user's observations. Instead of showing the user their true observations, we synthesize new observations that lead to more accurate internal state estimates when processed by the user. We refer to this method as assistive state estimation (ASE): an automated assistant uses the true observations to infer the state of the world, then generates a modified observation for the user to consume (e.g., through an augmented reality interface), and optimizes the modification to induce the user's new beliefs to match the assistant's current beliefs. We evaluate ASE in a user study with 12 participants who each perform four tasks: two tasks with known user biases -- bandwidth-limited image classification and a driving video game with observation delay -- and two with unknown biases that our method has to learn -- guided 2D navigation and a lunar lander teleoperation video game. A different assistance strategy emerges in each domain, such as quickly revealing informative pixels to speed up image classification, using a dynamics model to undo observation delay in driving, identifying nearby landmarks for navigation, and exaggerating a visual indicator of tilt in the lander game. The results show that ASE substantially improves the task performance of users with bandwidth constraints, observation delay, and other unknown biases.

arXiv:2208.03545

An Accurate and Explainable Deep Learning System Improves Interobserver Agreement in the Interpretation of Chest Radiograph

Recent artificial intelligence (AI) algorithms have achieved radiologist-level performance on various medical classification tasks. However, only a few studies addressed the localization of abnormal findings from CXR scans, which is essential in explaining the image-level classification to radiologists. We introduce in this paper an explainable deep learning system called VinDr-CXR that can classify a CXR scan into multiple thoracic diseases and, at the same time, localize most types of critical findings on the image. VinDr-CXR was trained on 51,485 CXR scans with radiologist-provided bounding box annotations. It demonstrated a comparable performance to experienced radiologists in classifying 6 common thoracic diseases on a retrospective validation set of 3,000 CXR scans, with a mean area under the receiver operating characteristic curve (AUROC) of 0.967 (95% confidence interval [CI]: 0.958-0.975). The VinDr-CXR was also externally validated in independent patient cohorts and showed its robustness. For the localization task with 14 types of lesions, our free-response receiver operating characteristic (FROC) analysis showed that the VinDr-CXR achieved a sensitivity of 80.2% at the rate of 1.0 false-positive lesion identified per scan. A prospective study was also conducted to measure the clinical impact of the VinDr-CXR in assisting six experienced radiologists. The results indicated that the proposed system, when used as a diagnosis supporting tool, significantly improved the agreement between radiologists themselves with an increase of 1.5% in mean Fleiss' Kappa. We also observed that, after the radiologists consulted VinDr-CXR's suggestions, the agreement between each of them and the system was remarkably increased by 3.3% in mean Cohen's Kappa.

arXiv:2210.15128

MMFL-Net: Multi-scale and Multi-granularity Feature Learning for Cross-domain Fashion Retrieval

Instance-level image retrieval in fashion is a challenging issue owing to its increasing importance in real-scenario visual fashion search. Cross-domain fashion retrieval aims to match the unconstrained customer images as queries for photographs provided by retailers; however, it is a difficult task due to a wide range of consumer-to-shop (C2S) domain discrepancies and also considering that clothing image is vulnerable to various non-rigid deformations. To this end, we propose a novel multi-scale and multi-granularity feature learning network (MMFL-Net), which can jointly learn global-local aggregation feature representations of clothing images in a unified framework, aiming to train a cross-domain model for C2S fashion visual similarity. First, a new semantic-spatial feature fusion part is designed to bridge the semantic-spatial gap by applying top-down and bottom-up bidirectional multi-scale feature fusion. Next, a multi-branch deep network architecture is introduced to capture global salient, part-informed, and local detailed information, and extracting robust and discrimination feature embedding by integrating the similarity learning of coarse-to-fine embedding with the multiple granularities. Finally, the improved trihard loss, center loss, and multi-task classification loss are adopted for our MMFL-Net, which can jointly optimize intra-class and inter-class distance and thus explicitly improve intra-class compactness and inter-class discriminability between its visual representations for feature learning. Furthermore, our proposed model also combines the multi-task attribute recognition and classification module with multi-label semantic attributes and product ID labels. Experimental results demonstrate that our proposed MMFL-Net achieves significant improvement over the state-of-the-art methods on the two datasets, DeepFashion-C2S and Street2Shop.

arXiv:1811.09043

Detecting Adversarial Perturbations Through Spatial Behavior in Activation Spaces

Neural network based classifiers are still prone to manipulation through adversarial perturbations. State of the art attacks can overcome most of the defense or detection mechanisms suggested so far, and adversaries have the upper hand in this arms race. Adversarial examples are designed to resemble the normal input from which they were constructed, while triggering an incorrect classification. This basic design goal leads to a characteristic spatial behavior within the context of Activation Spaces, a term coined by the authors to refer to the hyperspaces formed by the activation values of the network's layers. Within the output of the first layers of the network, an adversarial example is likely to resemble normal instances of the source class, while in the final layers such examples will diverge towards the adversary's target class. The steps below enable us to leverage this inherent shift from one class to another in order to form a novel adversarial example detector. We construct Euclidian spaces out of the activation values of each of the deep neural network layers. Then, we induce a set of k-nearest neighbor classifiers (k-NN), one per activation space of each neural network layer, using the non-adversarial examples. We leverage those classifiers to produce a sequence of class labels for each nonperturbed input sample and estimate the a priori probability for a class label change between one activation space and another. During the detection phase we compute a sequence of classification labels for each input using the trained classifiers. We then estimate the likelihood of those classification sequences and show that adversarial sequences are far less likely than normal ones. We evaluated our detection method against the state of the art C&W attack method, using two image classification datasets (MNIST, CIFAR-10) reaching an AUC 0f 0.95 for the CIFAR-10 dataset.

arXiv:2206.13383

Mushroom image recognition and distance generation based on attention-mechanism model and genetic information

The species identification of Macrofungi, i.e. mushrooms, has always been a challenging task. There are still a large number of poisonous mushrooms that have not been found, which poses a risk to people's life. However, the traditional identification method requires a large number of experts with knowledge in the field of taxonomy for manual identification, it is not only inefficient but also consumes a lot of manpower and capital costs. In this paper, we propose a new model based on attention-mechanism, MushroomNet, which applies the lightweight network MobileNetV3 as the backbone model, combined with the attention structure proposed by us, and has achieved excellent performance in the mushroom recognition task. On the public dataset, the test accuracy of the MushroomNet model has reached 83.9%, and on the local dataset, the test accuracy has reached 77.4%. The proposed attention mechanisms well focused attention on the bodies of mushroom image for mixed channel attention and the attention heat maps visualized by Grad-CAM. Further, in this study, genetic distance was added to the mushroom image recognition task, the genetic distance was used as the representation space, and the genetic distance between each pair of mushroom species in the dataset was used as the embedding of the genetic distance representation space, so as to predict the image distance and species. identify. We found that using the MES activation function can predict the genetic distance of mushrooms very well, but the accuracy is lower than that of SoftMax. The proposed MushroomNet was demonstrated it shows great potential for automatic and online mushroom image and the proposed automatic procedure would assist and be a reference to traditional mushroom classification.

arXiv:1910.10371

Semi-supervised Multi-domain Multi-task Training for Metastatic Colon Lymph Node Diagnosis From Abdominal CT

The diagnosis of the presence of metastatic lymph nodes from abdominal computed tomography (CT) scans is an essential task performed by radiologists to guide radiation and chemotherapy treatment. State-of-the-art deep learning classifiers trained for this task usually rely on a training set containing CT volumes and their respective image-level (i.e., global) annotation. However, the lack of annotations for the localisation of the regions of interest (ROIs) containing lymph nodes can limit classification accuracy due to the small size of the relevant ROIs in this problem. The use of lymph node ROIs together with global annotations in a multi-task training process has the potential to improve classification accuracy, but the high cost involved in obtaining the ROI annotation for the same samples that have global annotations is a roadblock for this alternative. We address this limitation by introducing a new training strategy from two data sets: one containing the global annotations, and another (publicly available) containing only the lymph node ROI localisation. We term our new strategy semi-supervised multi-domain multi-task training, where the goal is to improve the diagnosis accuracy on the globally annotated data set by incorporating the ROI annotations from a different domain. Using a private data set containing global annotations and a public data set containing lymph node ROI localisation, we show that our proposed training mechanism improves the area under the ROC curve for the classification task compared to several training method baselines.

arXiv:2008.08525

"Name that manufacturer". Relating image acquisition bias with task complexity when training deep learning models: experiments on head CT

As interest in applying machine learning techniques for medical images continues to grow at a rapid pace, models are starting to be developed and deployed for clinical applications. In the clinical AI model development lifecycle (described by Lu et al. [1]), a crucial phase for machine learning scientists and clinicians is the proper design and collection of the data cohort. The ability to recognize various forms of biases and distribution shifts in the dataset is critical at this step. While it remains difficult to account for all potential sources of bias, techniques can be developed to identify specific types of bias in order to mitigate their impact. In this work we analyze how the distribution of scanner manufacturers in a dataset can contribute to the overall bias of deep learning models. We evaluate convolutional neural networks (CNN) for both classification and segmentation tasks, specifically two state-of-the-art models: ResNet [2] for classification and U-Net [3] for segmentation. We demonstrate that CNNs can learn to distinguish the imaging scanner manufacturer and that this bias can substantially impact model performance for both classification and segmentation tasks. By creating an original synthesis dataset of brain data mimicking the presence of more or less subtle lesions we also show that this bias is related to the difficulty of the task. Recognition of such bias is critical to develop robust, generalizable models that will be crucial for clinical applications in real-world data distributions.

arXiv:1702.04069공식 코드 · Papers with Code

SSPP-DAN: Deep Domain Adaptation Network for Face Recognition with Single Sample Per Person

Real-world face recognition using a single sample per person (SSPP) is a challenging task. The problem is exacerbated if the conditions under which the gallery image and the probe set are captured are completely different. To address these issues from the perspective of domain adaptation, we introduce an SSPP domain adaptation network (SSPP-DAN). In the proposed approach, domain adaptation, feature extraction, and classification are performed jointly using a deep architecture with domain-adversarial training. However, the SSPP characteristic of one training sample per class is insufficient to train the deep architecture. To overcome this shortage, we generate synthetic images with varying poses using a 3D face model. Experimental evaluations using a realistic SSPP dataset show that deep domain adaptation and image synthesis complement each other and dramatically improve accuracy. Experiments on a benchmark dataset using the proposed approach show state-of-the-art performance. All the dataset and the source code can be found in our online repository (https://github.com/csehong/SSPP-DAN).

arXiv:1503.08909

Beyond Short Snippets: Deep Networks for Video Classification

Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation and retrieval. In this work we propose and evaluate several deep neural network architectures to combine image information across a video over longer time periods than previously attempted. We propose two methods capable of handling full length videos. The first method explores various convolutional temporal feature pooling architectures, examining the various design choices which need to be made when adapting a CNN for this task. The second proposed method explicitly models the video as an ordered sequence of frames. For this purpose we employ a recurrent neural network that uses Long Short-Term Memory (LSTM) cells which are connected to the output of the underlying CNN. Our best networks exhibit significant performance improvements over previously published results on the Sports 1 million dataset (73.1% vs. 60.9%) and the UCF-101 datasets with (88.6% vs. 88.0%) and without additional optical flow information (82.6% vs. 72.8%).