PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:1611.02886

Node-Adapt, Path-Adapt and Tree-Adapt:Model-Transfer Domain Adaptation for Random Forest

Random Forest (RF) is a successful paradigm for learning classifiers due to its ability to learn from large feature spaces and seamlessly integrate multi-class classification, as well as the achieved accuracy and processing efficiency. However, as many other classifiers, RF requires domain adaptation (DA) provided that there is a mismatch between the training (source) and testing (target) domains which provokes classification degradation. Consequently, different RF-DA methods have been proposed, which not only require target-domain samples but revisiting the source-domain ones, too. As novelty, we propose three inherently different methods (Node-Adapt, Path-Adapt and Tree-Adapt) that only require the learned source-domain RF and a relatively few target-domain samples for DA, i.e. source-domain samples do not need to be available. To assess the performance of our proposals we focus on image-based object detection, using the pedestrian detection problem as challenging proof-of-concept. Moreover, we use the RF with expert nodes because it is a competitive patch-based pedestrian model. We test our Node-, Path- and Tree-Adapt methods in standard benchmarks, showing that DA is largely achieved.

arXiv:1909.01040공식 코드 · Papers with Code

A Geometry-Sensitive Approach for Photographic Style Classification

Photographs are characterized by different compositional attributes like the Rule of Thirds, depth of field, vanishing-lines etc. The presence or absence of one or more of these attributes contributes to the overall artistic value of an image. In this work, we analyze the ability of deep learning based methods to learn such photographic style attributes. We observe that although a standard CNN learns the texture and appearance based features reasonably well, its understanding of global and geometric features is limited by two factors. First, the data-augmentation strategies (cropping, warping, etc.) distort the composition of a photograph and affect the performance. Secondly, the CNN features, in principle, are translation-invariant and appearance-dependent. But some geometric properties important for aesthetics, e.g. the Rule of Thirds (RoT), are position-dependent and appearance-invariant. Therefore, we propose a novel input representation which is geometry-sensitive, position-cognizant and appearance-invariant. We further introduce a two-column CNN architecture that performs better than the state-of-the-art (SoA) in photographic style classification. From our results, we observe that the proposed network learns both the geometric and appearance-based attributes better than the SoA.

arXiv:1909.12117

Balanced Binary Neural Networks with Gated Residual

Binary neural networks have attracted numerous attention in recent years. However, mainly due to the information loss stemming from the biased binarization, how to preserve the accuracy of networks still remains a critical issue. In this paper, we attempt to maintain the information propagated in the forward process and propose a Balanced Binary Neural Networks with Gated Residual (BBG for short). First, a weight balanced binarization is introduced to maximize information entropy of binary weights, and thus the informative binary weights can capture more information contained in the activations. Second, for binary activations, a gated residual is further appended to compensate their information loss during the forward process, with a slight overhead. Both techniques can be wrapped as a generic network module that supports various network architectures for different tasks including classification and detection. We evaluate our BBG on image classification tasks over CIFAR-10/100 and ImageNet and on detection task over Pascal VOC. The experimental results show that BBG-Net performs remarkably well across various network architectures such as VGG, ResNet and SSD with the superior performance over state-of-the-art methods in terms of memory consumption, inference speed and accuracy.

arXiv:2101.05091

MRI Images, Brain Lesions and Deep Learning

Medical brain image analysis is a necessary step in Computer Assisted /Aided Diagnosis (CAD) systems. Advancements in both hardware and software in the past few years have led to improved segmentation and classification of various diseases. In the present work, we review the published literature on systems and algorithms that allow for classification, identification, and detection of White Matter Hyperintensities (WMHs) of brain MRI images specifically in cases of ischemic stroke and demyelinating diseases. For the selection criteria, we used the bibliometric networks. Out of a total of 140 documents we selected 38 articles that deal with the main objectives of this study. Based on the analysis and discussion of the revised documents, there is constant growth in the research and proposal of new models of deep learning to achieve the highest accuracy and reliability of the segmentation of ischemic and demyelinating lesions. Models with indicators (Dice Score, DSC: 0.99) were found, however with little practical application due to the uses of small datasets and lack of reproducibility. Therefore, the main conclusion is to establish multidisciplinary research groups to overcome the gap between CAD developments and their complete utilization in the clinical environment.

arXiv:2106.02964

A Review of Machine Learning Classification Using Quantum Annealing for Real-world Applications

Optimizing the training of a machine learning pipeline helps in reducing training costs and improving model performance. One such optimizing strategy is quantum annealing, which is an emerging computing paradigm that has shown potential in optimizing the training of a machine learning model. The implementation of a physical quantum annealer has been realized by D-Wave systems and is available to the research community for experiments. Recent experimental results on a variety of machine learning applications using quantum annealing have shown interesting results where the performance of classical machine learning techniques is limited by limited training data and high dimensional features. This article explores the application of D-Wave's quantum annealer for optimizing machine learning pipelines for real-world classification problems. We review the application domains on which a physical quantum annealer has been used to train machine learning classifiers. We discuss and analyze the experiments performed on the D-Wave quantum annealer for applications such as image recognition, remote sensing imagery, computational biology, and particle physics. We discuss the possible advantages and the problems for which quantum annealing is likely to be advantageous over classical computation.

arXiv:2112.03951

Few-Shot Image Classification Along Sparse Graphs

Few-shot learning remains a challenging problem, with unsatisfactory 1-shot accuracies for most real-world data. Here, we present a different perspective for data distributions in the feature space of a deep network and show how to exploit it for few-shot learning. First, we observe that nearest neighbors in the feature space are with high probability members of the same class while generally two random points from one class are not much closer to each other than points from different classes. This observation suggests that classes in feature space form sparse, loosely connected graphs instead of dense clusters. To exploit this property, we propose using a small amount of label propagation into the unlabeled space and then using a kernel PCA reconstruction error as decision boundary for the feature-space data distribution of each class. Using this method, which we call "K-Prop," we demonstrate largely improved few-shot learning performances (e.g., 83% accuracy for 1-shot 5-way classification on the RESISC45 satellite-images dataset) for datasets for which a backbone network can be trained with high within-class nearest-neighbor probabilities. We demonstrate this relationship using six different datasets.

arXiv:2202.13755공식 코드 · Papers with Code

Towards Robust Stacked Capsule Autoencoder with Hybrid Adversarial Training

Capsule networks (CapsNets) are new neural networks that classify images based on the spatial relationships of features. By analyzing the pose of features and their relative positions, it is more capable to recognize images after affine transformation. The stacked capsule autoencoder (SCAE) is a state-of-the-art CapsNet, and achieved unsupervised classification of CapsNets for the first time. However, the security vulnerabilities and the robustness of the SCAE has rarely been explored. In this paper, we propose an evasion attack against SCAE, where the attacker can generate adversarial perturbations based on reducing the contribution of the object capsules in SCAE related to the original category of the image. The adversarial perturbations are then applied to the original images, and the perturbed images will be misclassified. Furthermore, we propose a defense method called Hybrid Adversarial Training (HAT) against such evasion attacks. HAT makes use of adversarial training and adversarial distillation to achieve better robustness and stability. We evaluate the defense method and the experimental results show that the refined SCAE model can achieve 82.14% classification accuracy under evasion attack. The source code is available at https://github.com/FrostbiteXSW/SCAE_Defense.

arXiv:2203.05740공식 코드 · Papers with Code

QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization

Recently, post-training quantization (PTQ) has driven much attention to produce efficient neural networks without long-time retraining. Despite its low cost, current PTQ works tend to fail under the extremely low-bit setting. In this study, we pioneeringly confirm that properly incorporating activation quantization into the PTQ reconstruction benefits the final accuracy. To deeply understand the inherent reason, a theoretical framework is established, indicating that the flatness of the optimized low-bit model on calibration and test data is crucial. Based on the conclusion, a simple yet effective approach dubbed as QDROP is proposed, which randomly drops the quantization of activations during PTQ. Extensive experiments on various tasks including computer vision (image classification, object detection) and natural language processing (text classification and question answering) prove its superiority. With QDROP, the limit of PTQ is pushed to the 2-bit activation for the first time and the accuracy boost can be up to 51.49%. Without bells and whistles, QDROP establishes a new state of the art for PTQ. Our code is available at https://github.com/wimh966/QDrop and has been integrated into MQBench (https://github.com/ModelTC/MQBench)

arXiv:2203.12281

Efficient Fully Distributed Federated Learning with Adaptive Local Links

Nowadays, data-driven, machine and deep learning approaches have provided unprecedented performance in various complex tasks, including image classification and object detection, and in a variety of application areas, like autonomous vehicles, medical imaging and wireless communications. Traditionally, such approaches have been deployed, along with the involved datasets, on standalone devices. Recently, a shift has been observed towards the so-called Edge Machine Learning, in which centralized architectures are adopted that allow multiple devices with local computational and storage resources to collaborate with the assistance of a centralized server. The well-known federated learning approach is able to utilize such architectures by allowing the exchange of only parameters with the server, while keeping the datasets private to each contributing device. In this work, we propose a fully distributed, diffusion-based learning algorithm that does not require a central server and propose an adaptive combination rule for the cooperation of the devices. By adopting a classification task on the MNIST dataset, the efficacy of the proposed algorithm over corresponding counterparts is demonstrated via the reduction of the number of collaboration rounds required to achieve an acceptable accuracy level in non- IID dataset scenarios.

arXiv:2206.10531공식 코드 · Papers with Code

Neural Transformers for Intraductal Papillary Mucosal Neoplasms (IPMN) Classification in MRI images

Early detection of precancerous cysts or neoplasms, i.e., Intraductal Papillary Mucosal Neoplasms (IPMN), in pancreas is a challenging and complex task, and it may lead to a more favourable outcome. Once detected, grading IPMNs accurately is also necessary, since low-risk IPMNs can be under surveillance program, while high-risk IPMNs have to be surgically resected before they turn into cancer. Current standards (Fukuoka and others) for IPMN classification show significant intra- and inter-operator variability, beside being error-prone, making a proper diagnosis unreliable. The established progress in artificial intelligence, through the deep learning paradigm, may provide a key tool for an effective support to medical decision for pancreatic cancer. In this work, we follow this trend, by proposing a novel AI-based IPMN classifier that leverages the recent success of transformer networks in generalizing across a wide variety of tasks, including vision ones. We specifically show that our transformer-based model exploits pre-training better than standard convolutional neural networks, thus supporting the sought architectural universalism of transformers in vision, including the medical image domain and it allows for a better interpretation of the obtained results.

arXiv:2211.05269

Generative Adversarial Networks for Weakly Supervised Generation and Evaluation of Brain Tumor Segmentations on MR Images

Segmentation of regions of interest (ROIs) for identifying abnormalities is a leading problem in medical imaging. Using machine learning for this problem generally requires manually annotated ground-truth segmentations, demanding extensive time and resources from radiologists. This work presents a weakly supervised approach that utilizes binary image-level labels, which are much simpler to acquire, to effectively segment anomalies in 2D magnetic resonance images without ground truth annotations. We train a generative adversarial network (GAN) that converts cancerous images to healthy variants, which are used along with localization seeds as priors to generate improved weakly supervised segmentations. The non-cancerous variants can also be used to evaluate the segmentations in a weakly supervised fashion, which allows for the most effective segmentations to be identified and then applied to downstream clinical classification tasks. On the Multimodal Brain Tumor Segmentation (BraTS) 2020 dataset, our proposed method generates and identifies segmentations that achieve test Dice coefficients of 83.91%. Using these segmentations for pathology classification results with a test AUC of 93.32% which is comparable to the test AUC of 95.80% achieved when using true segmentations.

arXiv:2304.02931공식 코드 · Papers with Code

Mask Detection and Classification in Thermal Face Images

Face masks are recommended to reduce the transmission of many viruses, especially SARS-CoV-2. Therefore, the automatic detection of whether there is a mask on the face, what type of mask is worn, and how it is worn is an important research topic. In this work, the use of thermal imaging was considered to analyze the possibility of detecting (localizing) a mask on the face, as well as to check whether it is possible to classify the type of mask on the face. The previously proposed dataset of thermal images was extended and annotated with the description of a type of mask and a location of a mask within a face. Different deep learning models were adapted. The best model for face mask detection turned out to be the Yolov5 model in the "nano" version, reaching mAP higher than 97% and precision of about 95%. High accuracy was also obtained for mask type classification. The best results were obtained for the convolutional neural network model built on an autoencoder initially trained in the thermal image reconstruction problem. The pretrained encoder was used to train a classifier which achieved an accuracy of 91%.

arXiv:2405.02366

Bayesian and Convolutional Networks for Hierarchical Morphological Classification of Galaxies

This work is focused on the morphological classification of galaxies following the Hubble sequence in which the different classes are arranged in a hierarchy. The proposed method, BCNN, is composed of two main modules. First, a convolutional neural network (CNN) is trained with images of the different classes of galaxies (image augmentation is carried out to balance some classes); the CNN outputs the probability for each class of the hierarchy, and its outputs/predictions feed the second module. The second module consists of a Bayesian network that represents the hierarchy and helps to improve the prediction accuracy by combining the predictions of the first phase while maintaining the hierarchical constraint (in a hierarchy, an instance associated with a node must be associated to all its ancestors), through probabilistic inference over the Bayesian network so that a consistent prediction is obtained. Different images from the Hubble telescope have been collected and labeled by experts, which are used to perform the experiments. The results show that BCNN performed better than several CNNs in multiple evaluation measures, reaching the next scores: 67% in exact match, 78% in accuracy, and 83% in hierarchical F-measure.

arXiv:2405.04717

Remote Diffusion

I explored adapting Stable Diffusion v1.5 for generating domain-specific satellite and aerial images in remote sensing. Recognizing the limitations of existing models like Midjourney and Stable Diffusion, trained primarily on natural RGB images and lacking context for remote sensing, I used the RSICD dataset to train a Stable Diffusion model with a loss of 0.2. I incorporated descriptive captions from the dataset for text-conditioning. Additionally, I created a synthetic dataset for a Land Use Land Classification (LULC) task, employing prompting techniques with RAG and ChatGPT and fine-tuning a specialized remote sensing LLM. However, I faced challenges with prompt quality and model performance. I trained a classification model (ResNet18) on the synthetic dataset achieving 49.48% test accuracy in TorchGeo to create a baseline. Quantitative evaluation through FID scores and qualitative feedback from domain experts assessed the realism and quality of the generated images and dataset. Despite extensive fine-tuning and dataset iterations, results indicated subpar image quality and realism, as indicated by high FID scores and domain-expert evaluation. These findings call attention to the potential of diffusion models in remote sensing while highlighting significant challenges related to insufficient pretraining data and computational resources.

arXiv:2509.15688v2cs.CV

PPS: 세밀한 분류를 위한 플러그 앤 플레이 단속적 시각

PPS: Plug-and-Play Saccadic Vision for Fine-Grained Classification

세밀한 시각 분류는 미묘하고 국소적인 단서를 구분하기 위해 고해상도 입력의 이점을 얻지만, 그 대가로 큰 계산량과 메모리 예산이 필요하다. 인간의 단속적 시각(saccadic vision)에서 영감을 받아, 우리는 공간 특징 맵을 가진 임의의 사전 학습 백본을 glimpse 유도 추론을 통해 단속적 분류기로 바꾸는 경량 확장을 제안한다. 구조상 추가되는 것은 작은 우선순위 헤드와 단일 교차 어텐션 융합 블록뿐이다. 가중치를 공유하는 동일한 인코더가 다운샘플링된 주변부 glance를 인코딩하고, 우선순위 헤드가 glimpse 우선순위 분포를 예측하는 데 쓰이는 공간 특징 맵을 내놓으며, 이 분포에서 샘플링한 고해상도 glimpse 크롭을 병렬로 다시 인코딩한다. 비최대 억제를 갖춘 순차 샘플러가 실행 시점에 설정 가능한 개수의 glimpse를 추출한다. 이어서 잔차 멀티헤드 교차 어텐션 블록이 glance를 glimpse들과 융합한다. 우선순위 맵의 품질을 높이기 위해, 경량의 이미지별 메모리 뱅크에서 얻은 glimpse별 정보 이득 목표로 우선순위 헤드를 학습시킨다. 이는 강화학습을 필요로 하지 않는다. 복잡도는 glimpse 수에 선형적이며 최대 메모리는 입력 해상도와 분리된다. 아홉 개의 벤치마크 전반에서 우리의 프레임워크는 기반 백본보다 일관되게 향상된 성능을 보인다.

arXiv:2509.02792v2cs.LG

구조화 기저함수 네트워크: 다양성을 제어할 수 있는 손실 중심 다중 가설 앙상블

Structured Basis Function Networks: Loss-Centric Multi-Hypothesis Ensembles with Controllable Diversity

앙상블 학습과 다중 가설 예측은 예측 성능과 강건성을 향상시키는 두 가지 상호 보완적인 패러다임이다. 본 연구는 예측 공간의 손실 유도 Bregman 중심(centroid) 기하에 착안한 지도 집계 메커니즘을 통해 이 두 패러다임을 통합하는 손실 인지형 앙상블 프레임워크인 구조화 기저함수 네트워크(Structured Basis Function Network, s-BFN)를 제안한다. 이 접근법은 기저 예측들의 구조화된 데이터셋을 구성하고 관측된 레이블에 대해 직접 모수적 결합기를 학습시키며, 중심 기반 정식화는 정확한 중심 해법이 아니라 기하학적 기준으로 사용되고, 다양성 제어 모수가 예측기 간의 특화 정도를 조절한다. 제안한 프레임워크는 표 형식 데이터, 이미지 인식, 대규모 시간 구조 비디오 분류를 포함한 회귀 및 분류 과제 전반에서 평가된다. 실험 결과 s-BFN은 평가된 모든 영역에서 강한 성능을 보이며 본 연구에서 고려한 집계 기준선들과 경쟁력이 있다. 가장 큰 성능 향상은 집계 용량과 제어된 다양성이 함께 이로운 고차원 및 시간 구조 설정에서 관찰되었으며, 더 단순한 표 형식 영역에서는 더 일찍 포화가 나타났다. 이러한 결과는 다양성, 앙상블 크기, 정확도 사이의 엄밀한 단조 관계가 아니라 용량-복잡도-다양성 간의 상충 관계를 부각한다.

arXiv:1703.04197

Automatic Skin Lesion Analysis using Large-scale Dermoscopy Images and Deep Residual Networks

Malignant melanoma has one of the most rapidly increasing incidences in the world and has a considerable mortality rate. Early diagnosis is particularly important since melanoma can be cured with prompt excision. Dermoscopy images play an important role in the non-invasive early detection of melanoma [1]. However, melanoma detection using human vision alone can be subjective, inaccurate and poorly reproducible even among experienced dermatologists. This is attributed to the challenges in interpreting images with diverse characteristics including lesions of varying sizes and shapes, lesions that may have fuzzy boundaries, different skin colors and the presence of hair [2]. Therefore, the automatic analysis of dermoscopy images is a valuable aid for clinical decision making and for image-based diagnosis to identify diseases such as melanoma [1-4]. Deep residual networks (ResNets) has achieved state-of-the-art results in image classification and detection related problems [5-8]. In this ISIC 2017 skin lesion analysis challenge [9], we propose to exploit the deep ResNets for robust visual features learning and representations.

arXiv:1603.08511공식 코드 · Papers with Code

Colorful Image Colorization

Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible color version of the photograph. This problem is clearly underconstrained, so previous approaches have either relied on significant user interaction or resulted in desaturated colorizations. We propose a fully automatic approach that produces vibrant and realistic colorizations. We embrace the underlying uncertainty of the problem by posing it as a classification task and use class-rebalancing at training time to increase the diversity of colors in the result. The system is implemented as a feed-forward pass in a CNN at test time and is trained on over a million color images. We evaluate our algorithm using a "colorization Turing test," asking human participants to choose between a generated and ground truth color image. Our method successfully fools humans on 32% of the trials, significantly higher than previous methods. Moreover, we show that colorization can be a powerful pretext task for self-supervised feature learning, acting as a cross-channel encoder. This approach results in state-of-the-art performance on several feature learning benchmarks.

arXiv:1503.06917

Unsupervised Video Analysis Based on a Spatiotemporal Saliency Detector

Visual saliency, which predicts regions in the field of view that draw the most visual attention, has attracted a lot of interest from researchers. It has already been used in several vision tasks, e.g., image classification, object detection, foreground segmentation. Recently, the spectrum analysis based visual saliency approach has attracted a lot of interest due to its simplicity and good performance, where the phase information of the image is used to construct the saliency map. In this paper, we propose a new approach for detecting spatiotemporal visual saliency based on the phase spectrum of the videos, which is easy to implement and computationally efficient. With the proposed algorithm, we also study how the spatiotemporal saliency can be used in two important vision task, abnormality detection and spatiotemporal interest point detection. The proposed algorithm is evaluated on several commonly used datasets with comparison to the state-of-art methods from the literature. The experiments demonstrate the effectiveness of the proposed approach to spatiotemporal visual saliency detection and its application to the above vision tasks

arXiv:1810.00319공식 코드 · Papers with Code

Modeling Uncertainty with Hedged Instance Embedding

Instance embeddings are an efficient and versatile image representation that facilitates applications like recognition, verification, retrieval, and clustering. Many metric learning methods represent the input as a single point in the embedding space. Often the distance between points is used as a proxy for match confidence. However, this can fail to represent uncertainty arising when the input is ambiguous, e.g., due to occlusion or blurriness. This work addresses this issue and explicitly models the uncertainty by hedging the location of each input in the embedding space. We introduce the hedged instance embedding (HIB) in which embeddings are modeled as random variables and the model is trained under the variational information bottleneck principle. Empirical results on our new N-digit MNIST dataset show that our method leads to the desired behavior of hedging its bets across the embedding space upon encountering ambiguous inputs. This results in improved performance for image matching and classification tasks, more structure in the learned embedding space, and an ability to compute a per-exemplar uncertainty measure that is correlated with downstream performance.