PyTorchKR Papers

“Image Classification”

총 18,385편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2505.24799

Beyond Pretty Pictures: Combined Single- and Multi-Image Super-resolution for Sentinel-2 Images

Super-resolution aims to increase the resolution of satellite images by reconstructing high-frequency details, which go beyond na\"ive upsampling. This has particular relevance for Earth observation missions like Sentinel-2, which offer frequent, regular coverage at no cost; but at coarse resolution. Its pixel footprint is too large to capture small features like houses, streets, or hedge rows. To address this, we present SEN4X, a hybrid super-resolution architecture that combines the advantages of single-image and multi-image techniques. It combines temporal oversampling from repeated Sentinel-2 acquisitions with a learned prior from high-resolution Pl\'eiades Neo data. In doing so, SEN4X upgrades Sentinel-2 imagery to 2.5 m ground sampling distance. We test the super-resolved images on urban land-cover classification in Hanoi, Vietnam. We find that they lead to a significant performance improvement over state-of-the-art super-resolution baselines.

arXiv:2611.18729v1cs.CV

SCALE: 병리학에서의 전체 슬라이드 반사실적 설명을 향하여

SCALE: Towards whole-slide counterfactual explanations in pathology

암 진단은 조직병리학적 평가에 의존하며, 종양 형태가 질병 분류를 이끌고 치료 결정에 정보를 제공한다. 딥러닝(DL) 모델은 조직병리 이미지로부터 진단 특성을 예측하는 데 뛰어나다. 작은 핵심 영역이 있는 일반적인 의료 영상과 달리 조직병리 이미지는 질감적이며 관련 질감이 이미지 전체에 걸쳐 있어, 관련 이미지 영역을 찾는 방식으로 DL 예측을 설명하기가 어렵다. 반사실적 설명은 "이미지에서 무엇이 바뀌었다면 모델의 예측이 달라졌을까"를 묻는 유망한 대안을 제공한다. 이를 위해 우리는 조직병리 DL 모델에 대한 이러한 반사실적 설명을 생성하는 프레임워크인 SCALE을 제안한다. 여러 암 유형에 걸친 아홉 가지 반사실적 방향에서, SCALE은 생물학적 타당성을 유지하면서 예측을 의도한 목표 쪽으로 일관되게 이동시키는 전체 슬라이드 반사실적 설명을 생성한다. 전문의 자격을 가진 병리학자 여섯 명의 블라인드 평가에서 SCALE은 더 높은 형태학적 타당성(기준선 대비 승률 91.7%)과 유망한 반사실적 효과(목표 일관성 96.7%)를 보였다.

arXiv:1912.00233

Convolutional neural networks model improvements using demographics and image processing filters on chest x-rays

Purpose: The purpose of this study was to observe change in accuracies of convolutional neural networks (CNN) models (ratio of correct classifications to total predictions) on thoracic radiological images by creating different binary classification models based on age, gender, and image pre-processing filters on 14 pathologies. Methodology: This is a quantitative research exploring variation in CNN model accuracies. Radiological thoracic images were divided by age and gender and pre-processed by various image processing filters. Findings: We found partial support for enhancement to model accuracies by segregating modeling images by age and gender and applying image processing filters even though image processing filters are sometimes thought of as information filters. Research limitations: This study may be biased because it is based on radiological images by another research that tagged the images using an automated process that was not checked by a human. Practical implications: Researchers may want to focus on creating models segregated by demographics and pre-process the modeling images using image processing filters. Practitioners developing assistive technologies for thoracic diagnoses may benefit from incorporating demographics and employing multiple models simultaneously with varying statistical likelihood. Originality/value: This study uses demographics in model creation and utilizes image processing filters to improve model performance. Keywords: Convolutional Neural Network (CNN), Chest X-Ray, ChestX-ray14, Lung, Atelectasis, Cardiomegaly, Consolidation, Edema, Effusion, Emphysema, Infiltration, Mass, Nodule, Pleural Thickening, Pneumonia, Pneumathorax

arXiv:1601.00978

Crater Detection via Convolutional Neural Networks

Craters are among the most studied geomorphic features in the Solar System because they yield important information about the past and present geological processes and provide information about the relative ages of observed geologic formations. We present a method for automatic crater detection using advanced machine learning to deal with the large amount of satellite imagery collected. The challenge of automatically detecting craters comes from their is complex surface because their shape erodes over time to blend into the surface. Bandeira provided a seminal dataset that embodied this challenge that is still an unsolved pattern recognition problem to this day. There has been work to solve this challenge based on extracting shape and contrast features and then applying classification models on those features. The limiting factor in this existing work is the use of hand crafted filters on the image such as Gabor or Sobel filters or Haar features. These hand crafted methods rely on domain knowledge to construct. We would like to learn the optimal filters and features based on training examples. In order to dynamically learn filters and features we look to Convolutional Neural Networks (CNNs) which have shown their dominance in computer vision. The power of CNNs is that they can learn image filters which generate features for high accuracy classification.

arXiv:1410.0389

Learning to Transfer Privileged Information

We introduce a learning framework called learning using privileged information (LUPI) to the computer vision field. We focus on the prototypical computer vision problem of teaching computers to recognize objects in images. We want the computers to be able to learn faster at the expense of providing extra information during training time. As additional information about the image data, we look at several scenarios that have been studied in computer vision before: attributes, bounding boxes and image tags. The information is privileged as it is available at training time but not at test time. We explore two maximum-margin techniques that are able to make use of this additional source of information, for binary and multiclass object classification. We interpret these methods as learning easiness and hardness of the objects in the privileged space and then transferring this knowledge to train a better classifier in the original space. We provide a thorough analysis and comparison of information transfer from privileged to the original data spaces for both LUPI methods. Our experiments show that incorporating privileged information can improve the classification accuracy. Finally, we conduct user studies to understand which samples are easy and which are hard for human learning, and explore how this information is related to easy and hard samples when learning a classifier.

arXiv:1903.07054공식 코드 · Papers with Code

Adversarial Attacks on Deep Neural Networks for Time Series Classification

Time Series Classification (TSC) problems are encountered in many real life data mining tasks ranging from medicine and security to human activity recognition and food safety. With the recent success of deep neural networks in various domains such as computer vision and natural language processing, researchers started adopting these techniques for solving time series data mining problems. However, to the best of our knowledge, no previous work has considered the vulnerability of deep learning models to adversarial time series examples, which could potentially make them unreliable in situations where the decision taken by the classifier is crucial such as in medicine and security. For computer vision problems, such attacks have been shown to be very easy to perform by altering the image and adding an imperceptible amount of noise to trick the network into wrongly classifying the input image. Following this line of work, we propose to leverage existing adversarial attack mechanisms to add a special noise to the input time series in order to decrease the network's confidence when classifying instances at test time. Our results reveal that current state-of-the-art deep learning time series classifiers are vulnerable to adversarial attacks which can have major consequences in multiple domains such as food safety and quality assurance.

arXiv:2203.10435

Vision Transformer with Convolutions Architecture Search

Transformers exhibit great advantages in handling computer vision tasks. They model image classification tasks by utilizing a multi-head attention mechanism to process a series of patches consisting of split images. However, for complex tasks, Transformer in computer vision not only requires inheriting a bit of dynamic attention and global context, but also needs to introduce features concerning noise reduction, shifting, and scaling invariance of objects. Therefore, here we take a step forward to study the structural characteristics of Transformer and convolution and propose an architecture search method-Vision Transformer with Convolutions Architecture Search (VTCAS). The high-performance backbone network searched by VTCAS introduces the desirable features of convolutional neural networks into the Transformer architecture while maintaining the benefits of the multi-head attention mechanism. The searched block-based backbone network can extract feature maps at different scales. These features are compatible with a wider range of visual tasks, such as image classification (32 M parameters, 82.0% Top-1 accuracy on ImageNet-1K) and object detection (50.4% mAP on COCO2017). The proposed topology based on the multi-head attention mechanism and CNN adaptively associates relational features of pixels with multi-scale features of objects. It enhances the robustness of the neural network for object recognition, especially in the low illumination indoor scene.

arXiv:2403.04547

CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?

We study the effectiveness of data-balancing for mitigating biases in contrastive language-image pretraining (CLIP), identifying areas of strength and limitation. First, we reaffirm prior conclusions that CLIP models can inadvertently absorb societal stereotypes. To counter this, we present a novel algorithm, called Multi-Modal Moment Matching (M4), designed to reduce both representation and association biases (i.e. in first- and second-order statistics) in multimodal data. We use M4 to conduct an in-depth analysis taking into account various factors, such as the model, representation, and data size. Our study also explores the dynamic nature of how CLIP learns and unlearns biases. In particular, we find that fine-tuning is effective in countering representation biases, though its impact diminishes for association biases. Also, data balancing has a mixed impact on quality: it tends to improve classification but can hurt retrieval. Interestingly, data and architectural improvements seem to mitigate the negative impact of data balancing on performance; e.g. applying M4 to SigLIP-B/16 with data quality filters improves COCO image-to-text retrieval @5 from 86% (without data balancing) to 87% and ImageNet 0-shot classification from 77% to 77.5%! Finally, we conclude with recommendations for improving the efficacy of data balancing in multimodal systems.

arXiv:2606.21590v2cs.CV

자기지도 학습에서 프로젝션 헤드로서의 방사 기저 함수 네트워크

Radial Basis Function Networks as Projection Heads in Self-Supervised Learning

자기지도 학습(SSL)은 일반적으로 백본(backbone) 인코더 뒤에 작은 다층 퍼셉트론(MLP) 프로젝션 헤드가 이어지는 구조에 의존하며, 이 프로젝션 헤드는 통상 학습 후 버려지고, 백본의 품질은 레이블이 있는 데이터에 대한 비용이 큰 선형 프로빙(linear probing)으로 평가된다. 우리는 프로젝터를 버리는 것을 포함한 이 접근법이 상당히 계산적으로 낭비적이라고 주장한다. 대신, 우리는 MLP 헤드를 방사 기저 함수 네트워크(RBFN)로 대체할 것을 제안하며, RBFN의 해석 가능한 중심(center) 및 형태(shape) 매개변수를 활용하여 레이블이나 별도의 분류기 없이 표현(representation) 품질을 판단할 수 있다. 이를 위해 학습 중 학습된 커널 중심과 형태로만부터 유도된 새로운 레이블 없는 품질 지표인 Scale-Normalized Separation(SNS)을 도입한다. MoCo, SimCLR, BYOL, SwAV, SimSiam 다섯 가지 대표적인 SSL 아키텍처와 네 가지 이미지 분류 데이터셋에서, RBFN 프로젝션 헤드가 표준 MLP 프로젝터의 경쟁력 있는 드롭인(drop-in) 대체재임을 보여준다. 우리는 가우시안 방사 기저 함수(Gaussian radial basis function)로 활성화된 세 개의 RBF 층으로 구성할 것을 권장한다. 게다가 SNS는 확립된 로지스틱 회귀(logistic regression) 지표와 강함에서 매우 강함까지의 양의 상관관계를 보이며, 학습된 RBFN 프로젝터가 백본 표현 품질의 신뢰할 수 있는 대리(proxy) 지표로 작용할 수 있음을 보여준다. 또한 표현 학습에 대한 재현 가능한 연구를 촉진하기 위해 Google Open Images V7을 기반으로 한 새로운 PyTorch 호환 이미지 분류 데이터셋을 공개한다.

arXiv:1710.11309

Tumor Classification and Segmentation of MR Brain Images

The diagnosis and segmentation of tumors using any medical diagnostic tool can be challenging due to the varying nature of this pathology. Magnetic Reso- nance Imaging (MRI) is an established diagnostic tool for various diseases and disorders and plays a major role in clinical neuro-diagnosis. Supplementing this technique with automated classification and segmentation tools is gaining importance, to reduce errors and time needed to make a conclusive diagnosis. In this paper a simple three-step algorithm is proposed; (1) identification of patients that present with tumors, (2) automatic selection of abnormal slices of the patients, and (3) segmentation and detection of the tumor. Features were extracted by using discrete wavelet transform on the normalized images and classified by support vector machine (for step (1)) and random forest (for step (2)). The 400 subjects were divided in a 3:1 ratio between training and test with no overlap. This study is novel in terms of use of data, as it employed the entire T2 weighted slices as a single image for classification and a unique combination of contralateral approach with patch thresholding for segmentation, which does not require a training set or a template as is used by most segmentation studies. Using the proposed method, the tumors were segmented accurately with a classification accuracy of 95% with 100% specificity and 90% sensitivity.

arXiv:1906.04591

CNN depth analysis with different channel inputs for Acoustic Scene Classification

Acoustic scene classification (ASC) has been approached in the last years using deep learning techniques such as convolutional neural networks or recurrent neural networks. Many state-of-the-art solutions are based on image classification frameworks and, as such, a 2D representation of the audio signal is considered for training these networks. Finding the most suitable audio representation is still a research area of interest. In this paper, different log-Mel representations and combinations are analyzed. Experiments show that the best results are obtained using the harmonic and percussive components plus the difference between left and right stereo channels, (L-R). On the other hand, it is a common strategy to ensemble different models in order to increase the final accuracy. Even though averaging different model predictions is a common choice, an exhaustive analysis of different ensemble techniques has not been presented in ASC problems. In this paper, geometric and arithmetic mean plus the Ordered Weighted Averaging (OWA) operator are studied as aggregation operators for the output of the different models of the ensemble. Finally, the work carried out in this paper is highly oriented towards real-time implementations. In this context, as the number of applications for audio classification on edge devices is increasing exponentially, we also analyze different network depths and efficient solutions for aggregating ensemble predictions.

arXiv:2001.09614

Convolution Neural Network Architecture Learning for Remote Sensing Scene Classification

Remote sensing image scene classification is a fundamental but challenging task in understanding remote sensing images. Recently, deep learning-based methods, especially convolutional neural network-based (CNN-based) methods have shown enormous potential to understand remote sensing images. CNN-based methods meet with success by utilizing features learned from data rather than features designed manually. The feature-learning procedure of CNN largely depends on the architecture of CNN. However, most of the architectures of CNN used for remote sensing scene classification are still designed by hand which demands a considerable amount of architecture engineering skills and domain knowledge, and it may not play CNN's maximum potential on a special dataset. In this paper, we proposed an automatically architecture learning procedure for remote sensing scene classification. We designed a parameters space in which every set of parameters represents a certain architecture of CNN (i.e., some parameters represent the type of operators used in the architecture such as convolution, pooling, no connection or identity, and the others represent the way how these operators connect). To discover the optimal set of parameters for a given dataset, we introduced a learning strategy which can allow efficient search in the architecture space by means of gradient descent. An architecture generator finally maps the set of parameters into the CNN used in our experiments.

arXiv:2309.02670공식 코드 · Papers with Code

Progressive Attention Guidance for Whole Slide Vulvovaginal Candidiasis Screening

Vulvovaginal candidiasis (VVC) is the most prevalent human candidal infection, estimated to afflict approximately 75% of all women at least once in their lifetime. It will lead to several symptoms including pruritus, vaginal soreness, and so on. Automatic whole slide image (WSI) classification is highly demanded, for the huge burden of disease control and prevention. However, the WSI-based computer-aided VCC screening method is still vacant due to the scarce labeled data and unique properties of candida. Candida in WSI is challenging to be captured by conventional classification models due to its distinctive elongated shape, the small proportion of their spatial distribution, and the style gap from WSIs. To make the model focus on the candida easier, we propose an attention-guided method, which can obtain a robust diagnosis classification model. Specifically, we first use a pre-trained detection model as prior instruction to initialize the classification model. Then we design a Skip Self-Attention module to refine the attention onto the fined-grained features of candida. Finally, we use a contrastive learning method to alleviate the overfitting caused by the style gap of WSIs and suppress the attention to false positive regions. Our experimental results demonstrate that our framework achieves state-of-the-art performance. Code and example data are available at https://github.com/cjdbehumble/MICCAI2023-VVC-Screening.

arXiv:1810.01163

An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Images

Deep neural networks have established as a powerful tool for large scale supervised classification tasks. The state-of-the-art performances of deep neural networks are conditioned to the availability of large number of accurately labeled samples. In practice, collecting large scale accurately labeled datasets is a challenging and tedious task in most scenarios of remote sensing image analysis, thus cheap surrogate procedures are employed to label the dataset. Training deep neural networks on such datasets with inaccurate labels easily overfits to the noisy training labels and degrades the performance of the classification tasks drastically. To mitigate this effect, we propose an original solution with entropic optimal transportation. It allows to learn in an end-to-end fashion deep neural networks that are, to some extent, robust to inaccurately labeled samples. We empirically demonstrate on several remote sensing datasets, where both scene and pixel-based hyperspectral images are considered for classification. Our method proves to be highly tolerant to significant amounts of label noise and achieves favorable results against state-of-the-art methods.

arXiv:1907.00354

Difficulty-aware Meta-learning for Rare Disease Diagnosis

Rare diseases have extremely low-data regimes, unlike common diseases with large amount of available labeled data. Hence, to train a neural network to classify rare diseases with a few per-class data samples is very challenging, and so far, catches very little attention. In this paper, we present a difficulty-aware meta-learning method to address rare disease classifications and demonstrate its capability to classify dermoscopy images. Our key approach is to first train and construct a meta-learning model from data of common diseases, then adapt the model to perform rare disease classification.To achieve this, we develop the difficulty-aware meta-learning method that dynamically monitors the importance of learning tasks during the meta-optimization stage. To evaluate our method, we use the recent ISIC 2018 skin lesion classification dataset, and show that with only five samples per class, our model can quickly adapt to classify unseen classes by a high AUC of 83.3%. Also, we evaluated several rare disease classification results in the public Dermofit Image Library to demonstrate the potential of our method for real clinical practice.

arXiv:1908.07654

FusionNet: Incorporating Shape and Texture for Abnormality Detection in 3D Abdominal CT Scans

Automatic abnormality detection in abdominal CT scans can help doctors improve the accuracy and efficiency in diagnosis. In this paper we aim at detecting pancreatic ductal adenocarcinoma (PDAC), the most common pancreatic cancer. Taking the fact that the existence of tumor can affect both the shape and the texture of pancreas, we design a system to extract the shape and texture feature at the same time for detecting PDAC. In this paper we propose a two-stage method for this 3D classification task. First, we segment the pancreas into a binary mask. Second, a FusionNet is proposed to take both the binary mask and CT image as input and perform a binary classification. The optimal architecture of the FusionNet is obtained by searching a pre-defined functional space. We show that the classification results using either shape or texture information are complementary, and by fusing them with the optimized architecture, the performance improves by a large margin. Our method achieves a specificity of 97% and a sensitivity of 92% on 200 normal scans and 136 scans with PDAC.

arXiv:2006.00086

Synthesizing lesions using contextual GANs improves breast cancer classification on mammograms

Data scarcity and class imbalance are two fundamental challenges in many machine learning applications to healthcare. Breast cancer classification in mammography exemplifies these challenges, with a malignancy rate of around 0.5% in a screening population, which is compounded by the relatively small size of lesions (~1% of the image) in malignant cases. Simultaneously, the prevalence of screening mammography creates a potential abundance of non-cancer exams to use for training. Altogether, these characteristics lead to overfitting on cancer cases, while under-utilizing non-cancer data. Here, we present a novel generative adversarial network (GAN) model for data augmentation that can realistically synthesize and remove lesions on mammograms. With self-attention and semi-supervised learning components, the U-net-based architecture can generate high resolution (256x256px) outputs, as necessary for mammography. When augmenting the original training set with the GAN-generated samples, we find a significant improvement in malignancy classification performance on a test set of real mammogram patches. Overall, the empirical results of our algorithm and the relevance to other medical imaging paradigms point to potentially fruitful further applications.

arXiv:2011.11538공식 코드 · Papers with Code

Exploring Alternatives to Softmax Function

Softmax function is widely used in artificial neural networks for multiclass classification, multilabel classification, attention mechanisms, etc. However, its efficacy is often questioned in literature. The log-softmax loss has been shown to belong to a more generic class of loss functions, called spherical family, and its member log-Taylor softmax loss is arguably the best alternative in this class. In another approach which tries to enhance the discriminative nature of the softmax function, soft-margin softmax (SM-softmax) has been proposed to be the most suitable alternative. In this work, we investigate Taylor softmax, SM-softmax and our proposed SM-Taylor softmax, an amalgamation of the earlier two functions, as alternatives to softmax function. Furthermore, we explore the effect of expanding Taylor softmax up to ten terms (original work proposed expanding only to two terms) along with the ramifications of considering Taylor softmax to be a finite or infinite series during backpropagation. Our experiments for the image classification task on different datasets reveal that there is always a configuration of the SM-Taylor softmax function that outperforms the normal softmax function and its other alternatives.

arXiv:2209.01858

Consistency-Based Semi-supervised Evidential Active Learning for Diagnostic Radiograph Classification

Deep learning approaches achieve state-of-the-art performance for classifying radiology images, but rely on large labelled datasets that require resource-intensive annotation by specialists. Both semi-supervised learning and active learning can be utilised to mitigate this annotation burden. However, there is limited work on combining the advantages of semi-supervised and active learning approaches for multi-label medical image classification. Here, we introduce a novel Consistency-based Semi-supervised Evidential Active Learning framework (CSEAL). Specifically, we leverage predictive uncertainty based on theories of evidence and subjective logic to develop an end-to-end integrated approach that combines consistency-based semi-supervised learning with uncertainty-based active learning. We apply our approach to enhance four leading consistency-based semi-supervised learning methods: Pseudo-labelling, Virtual Adversarial Training, Mean Teacher and NoTeacher. Extensive evaluations on multi-label Chest X-Ray classification tasks demonstrate that CSEAL achieves substantive performance improvements over two leading semi-supervised active learning baselines. Further, a class-wise breakdown of results shows that our approach can substantially improve accuracy on rarer abnormalities with fewer labelled samples.

arXiv:2505.08524

Attention-based Generative Latent Replay: A Continual Learning Approach for WSI Analysis

Whole slide image (WSI) classification has emerged as a powerful tool in computational pathology, but remains constrained by domain shifts, e.g., due to different organs, diseases, or institution-specific variations. To address this challenge, we propose an Attention-based Generative Latent Replay Continual Learning framework (AGLR-CL), in a multiple instance learning (MIL) setup for domain incremental WSI classification. Our method employs Gaussian Mixture Models (GMMs) to synthesize WSI representations and patch count distributions, preserving knowledge of past domains without explicitly storing original data. A novel attention-based filtering step focuses on the most salient patch embeddings, ensuring high-quality synthetic samples. This privacy-aware strategy obviates the need for replay buffers and outperforms other buffer-free counterparts while matching the performance of buffer-based solutions. We validate AGLR-CL on clinically relevant biomarker detection and molecular status prediction across multiple public datasets with diverse centers, organs, and patient cohorts. Experimental results confirm its ability to retain prior knowledge and adapt to new domains, offering an effective, privacy-preserving avenue for domain incremental continual learning in WSI classification.