PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2409.20132

Machine Learning in Industrial Quality Control of Glass Bottle Prints

In industrial manufacturing of glass bottles, quality control of bottle prints is necessary as numerous factors can negatively affect the printing process. Even minor defects in the bottle prints must be detected despite reflections in the glass or manufacturing-related deviations. In cooperation with our medium-sized industrial partner, two ML-based approaches for quality control of these bottle prints were developed and evaluated, which can also be used in this challenging scenario. Our first approach utilized different filters to supress reflections (e.g. Sobel or Canny) and image quality metrics for image comparison (e.g. MSE or SSIM) as features for different supervised classification models (e.g. SVM or k-Neighbors), which resulted in an accuracy of 84%. The images were aligned based on the ORB algorithm, which allowed us to estimate the rotations of the prints, which may serve as an indicator for anomalies in the manufacturing process. In our second approach, we fine-tuned different pre-trained CNN models (e.g. ResNet or VGG) for binary classification, which resulted in an accuracy of 87%. Utilizing Grad-Cam on our fine-tuned ResNet-34, we were able to localize and visualize frequently defective bottle print regions. This method allowed us to provide insights that could be used to optimize the actual manufacturing process. This paper also describes our general approach and the challenges we encountered in practice with data collection during ongoing production, unsupervised preselection, and labeling.

arXiv:2505.12897공식 코드 · Papers with Code

EPIC: Explanation of Pretrained Image Classification Networks via Prototype

Explainable AI (XAI) methods generally fall into two categories. Post-hoc approaches generate explanations for pre-trained models and are compatible with various neural network architectures. These methods often use feature importance visualizations, such as saliency maps, to indicate which input regions influenced the model's prediction. Unfortunately, they typically offer a coarse understanding of the model's decision-making process. In contrast, ante-hoc (inherently explainable) methods rely on specially designed model architectures trained from scratch. A notable subclass of these methods provides explanations through prototypes, representative patches extracted from the training data. However, prototype-based approaches have limitations: they require dedicated architectures, involve specialized training procedures, and perform well only on specific datasets. In this work, we propose EPIC (Explanation of Pretrained Image Classification), a novel approach that bridges the gap between these two paradigms. Like post-hoc methods, EPIC operates on pre-trained models without architectural modifications. Simultaneously, it delivers intuitive, prototype-based explanations inspired by ante-hoc techniques. To the best of our knowledge, EPIC is the first post-hoc method capable of fully replicating the core explanatory power of inherently interpretable models. We evaluate EPIC on benchmark datasets commonly used in prototype-based explanations, such as CUB-200-2011 and Stanford Cars, alongside large-scale datasets like ImageNet, typically employed by post-hoc methods. EPIC uses prototypes to explain model decisions, providing a flexible and easy-to-understand tool for creating clear, high-quality explanations.

arXiv:1911.06259

Restricted Boltzmann Machines for galaxy morphology classification with a quantum annealer

We present the application of Restricted Boltzmann Machines (RBMs) to the task of astronomical image classification using a quantum annealer built by D-Wave Systems. Morphological analysis of galaxies provides critical information for studying their formation and evolution across cosmic time scales. We compress galaxy images using principal component analysis to fit a representation on the quantum hardware. Then, we train RBMs with discriminative and generative algorithms, including contrastive divergence and hybrid generative-discriminative approaches, to classify different galaxy morphologies. The methods we compare include Quantum Annealing (QA), Markov Chain Monte Carlo (MCMC) Gibbs Sampling, and Simulated Annealing (SA) as well as machine learning algorithms like gradient boosted decision trees. We find that RBMs implemented on D-Wave hardware perform well, and that they show some classification performance advantages on small datasets, but they don't offer a broadly strategic advantage for this task. During this exploration, we analyzed the steps required for Boltzmann sampling with the D-Wave 2000Q, including a study of temperature estimation, and examined the impact of qubit noise by comparing and contrasting the original D-Wave 2000Q to the lower-noise version recently made available. While these analyses ultimately had minimal impact on the performance of the RBMs, we include them for reference.

arXiv:2003.08823

Conditional Gaussian Distribution Learning for Open Set Recognition

Deep neural networks have achieved state-of-the-art performance in a wide range of recognition/classification tasks. However, when applying deep learning to real-world applications, there are still multiple challenges. A typical challenge is that unknown samples may be fed into the system during the testing phase and traditional deep neural networks will wrongly recognize the unknown sample as one of the known classes. Open set recognition is a potential solution to overcome this problem, where the open set classifier should have the ability to reject unknown samples as well as maintain high classification accuracy on known classes. The variational auto-encoder (VAE) is a popular model to detect unknowns, but it cannot provide discriminative representations for known classification. In this paper, we propose a novel method, Conditional Gaussian Distribution Learning (CGDL), for open set recognition. In addition to detecting unknown samples, this method can also classify known samples by forcing different latent features to approximate different Gaussian models. Meanwhile, to avoid information hidden in the input vanishing in the middle layers, we also adopt the probabilistic ladder architecture to extract high-level abstract features. Experiments on several standard image datasets reveal that the proposed method significantly outperforms the baseline method and achieves new state-of-the-art results.

arXiv:2608.09236v1cs.LG

계층적 이미지 분류 연합학습에서의 레이블 세분성 왜곡

Label Granularity Skew in Federated Learning with Hierarchical Image Classification

연합학습(Federated Learning)은 로컬 데이터를 중앙 집중화하지 않고도 분산된 기기 간에 프라이버시를 보존하는 협업을 가능하게 합니다. 그러나 클라이언트는 데이터 분포뿐만 아니라 도메인 지식과 어노테이션 역량에서도 차이가 날 수 있습니다. 본 논문에서는 클라이언트들이 공유된 클래스 계층 내에서 서로 다른 상세도 수준의 분류 체계 일치 레이블을 제공하는, 연합 계층적 분류에서의 새로운 통계적 이질성 형태인 '레이블 세분성 왜곡(label granularity skew)'을 소개합니다. 이러한 이질성을 모델링하기 위해, 확률적 관계 이웃 분류기를 사용하여 클라이언트별 로컬 레이블 계층을 생성하고 실루엣 점수 기반 조대화(coarsening)를 통해 WordNet 가이드 계층을 구축합니다. 분석 결과, 강력하게 결합된 계층적 모델은 불완전한 지도(supervision)에 민감한 반면, 조건부 소프트맥스 분류기는 더 강건함을 보여줍니다. 이러한 통찰을 바탕으로, 브랜치별 분류기를 미세조정하고 연합 최적화를 통해 이를 집약하는 브랜치별 분리 미세조정(Branch-wise Decoupled Fine-Tuning, BDFT)과 그 연합 버전인 FedBDFT를 제안합니다. CIFAR-100, TinyImageNet, ImageNet에 대한 실험은 FedBDFT가 심각한 레이블 세분성 왜곡 상황에서 강건성을 크게 향상시키며, 왜곡도 수준 0.6 및 0.9에서 각각 평균 27.9%와 56.4%의 성능 향상을 달성함을 보여줍니다. 또한 제로샷(zero-shot) 결과는 FedBDFT가 보지 못한 세부 클래스에 대해서도 계층적 표현을 더 잘 보존함을 나타냅니다. 이러한 결과는 이질적인 레이블 세분성을 갖는 연합 계층적 분류에서 제안 방법의 효과성을 입증합니다.

arXiv:2106.05915

Anatomy-XNet: An Anatomy Aware Convolutional Neural Network for Thoracic Disease Classification in Chest X-rays

Thoracic disease detection from chest radiographs using deep learning methods has been an active area of research in the last decade. Most previous methods attempt to focus on the diseased organs of the image by identifying spatial regions responsible for significant contributions to the model's prediction. In contrast, expert radiologists first locate the prominent anatomical structures before determining if those regions are anomalous. Therefore, integrating anatomical knowledge within deep learning models could bring substantial improvement in automatic disease classification. Motivated by this, we propose Anatomy-XNet, an anatomy-aware attention-based thoracic disease classification network that prioritizes the spatial features guided by the pre-identified anatomy regions. We adopt a semi-supervised learning method by utilizing available small-scale organ-level annotations to locate the anatomy regions in large-scale datasets where the organ-level annotations are absent. The proposed Anatomy-XNet uses the pre-trained DenseNet-121 as the backbone network with two corresponding structured modules, the Anatomy Aware Attention (A$^3$) and Probabilistic Weighted Average Pooling (PWAP), in a cohesive framework for anatomical attention learning. We experimentally show that our proposed method sets a new state-of-the-art benchmark by achieving an AUC score of 85.78%, 92.07%, and, 84.04% on three publicly available large-scale CXR datasets--NIH, Stanford CheXpert, and MIMIC-CXR, respectively. This not only proves the efficacy of utilizing the anatomy segmentation knowledge to improve the thoracic disease classification but also demonstrates the generalizability of the proposed framework.

arXiv:2610.07384v1cs.CV

WildMatch: 야생동물 재식별을 위한 약지도 이미지 매처 적응

WildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification

카메라 트랩 영상에서 개별 동물을 재식별(re-identification)하는 것은 비침습적 야생동물 모니터링의 핵심인 인스턴스 검색 문제입니다. 즉, 쿼리 이미지를 통해 이미 알려진 동물들의 참조 세트에서 올바른 개체를 검색해야 합니다. 이를 위해서는 컴퓨터 비전(CV) 모델이 털, 피부 또는 기타 시각적 무늬의 고유한 국소 패턴을 인식할 수 있어야 합니다. 기존 접근 방식들은 이를 분류(classification) 문제로 보고 전역 임베딩(global embedding)을 학습하여 개체당 다수의 라벨링된 이미지를 요구하면서 국소적인 단서를 대체로 무시하거나, 사전 구축된 도메인 무관 이미지 매처를 그대로 적용합니다. 이러한 매처들은 대규모의 다양한 이미지 모음에서 사전학습(pre-training)되었지만, 사용 가능한 데이터셋(dataset)의 규모가 작고 대응점(correspondence) 수준의 주석이 부족하기 때문에 야생동물 영상에 적응시키는 것은 까다롭습니다. 본 연구에서는 키포인트 수준이나 기하학적 대응점에 대한 정답 레이블 없이 개체 식별(identity) 라벨만을 사용하여 사전학습된 키포인트 매처를 약지도(weakly supervised) 방식으로 적응시키는 방법을 다룹니다. 사전학습된 매처를 사용해 유의미한 이미지 쌍을 마이닝하고, 개체 일치 여부로부터 약한 양성 및 음성 지도 신호를 도출하며, 동일 개체 쌍에 대해서는 대응점을 강화하고 서로 다른 개체에 대해서는 이를 억제하도록 매칭 네트워크를 대조적으로 파인튜닝(fine-tuning)합니다. 오픈소스 야생동물 재식별 데이터셋 전반에서 본 접근 방식은 기존 기성 매처 및 최첨단 국소-전역 융합 기법보다 정확도를 향상시킵니다. 학습(training)에 사용되지 않은 별도 개체를 포함하는 오픈월드 프로토콜에서도, 학습 개체를 단순 암기하는 대신 전이 가능한 대응점 사전 분포(correspondence prior)를 학습합니다. 우리가 아는 한, 이는 동물 재식별을 위해 개체 지도 신호를 기반으로 매처 수준에서 적응을 수행한 최초의 연구입니다. 본 기법은 일반적인 모니터링 데이터셋에서 이미 확보 가능한 개체 주석만을 활용하여 이미지 매칭 모델을 야생동물 도메인에 데이터 효율적으로 특화할 수 있도록 지원합니다.

arXiv:1806.00183공식 코드 · Papers with Code

Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network

Hyperspectral image (HSI) denoising is a crucial preprocessing procedure to improve the performance of the subsequent HSI interpretation and applications. In this paper, a novel deep learning-based method for this task is proposed, by learning a non-linear end-to-end mapping between the noisy and clean HSIs with a combined spatial-spectral deep convolutional neural network (HSID-CNN). Both the spatial and spectral information are simultaneously assigned to the proposed network. In addition, multi-scale feature extraction and multi-level feature representation are respectively employed to capture both the multi-scale spatial-spectral feature and fuse the feature representations with different levels for the final restoration. The simulated and real-data experiments demonstrate that the proposed HSID-CNN outperforms many of the mainstream methods in both the quantitative evaluation indexes, visual effects, and HSI classification accuracy.

arXiv:1809.00340

Identifying Land Patterns from Satellite Imagery in Amazon Rainforest using Deep Learning

The Amazon rainforests have been suffering widespread damage, both via natural and artificial means. Every minute, it is estimated that the world loses forest cover the size of 48 football fields. Deforestation in the Amazon rainforest has led to drastically reduced biodiversity, loss of habitat, climate change, and other biological losses. In this respect, it has become essential to track how the nature of these forests change over time. Image classification using deep learning can help speed up this process by removing the manual task of classifying each image. Here, it is shown how convolutional neural networks can be used to track changes in land patterns in the Amazon rainforests. In this work, a testing accuracy of 96.71% was obtained. This can help governments and other agencies to track changes in land patterns more effectively and accurately.

arXiv:1905.06526공식 코드 · Papers with Code

Joint Learning of Neural Networks via Iterative Reweighted Least Squares

In this paper, we introduce the problem of jointly learning feed-forward neural networks across a set of relevant but diverse datasets. Compared to learning a separate network from each dataset in isolation, joint learning enables us to extract correlated information across multiple datasets to significantly improve the quality of learned networks. We formulate this problem as joint learning of multiple copies of the same network architecture and enforce the network weights to be shared across these networks. Instead of hand-encoding the shared network layers, we solve an optimization problem to automatically determine how layers should be shared between each pair of datasets. Experimental results show that our approach outperforms baselines without joint learning and those using pretraining-and-fine-tuning. We show the effectiveness of our approach on three tasks: image classification, learning auto-encoders, and image generation.

arXiv:2002.07434

A Modified Perturbed Sampling Method for Local Interpretable Model-agnostic Explanation

Explainability is a gateway between Artificial Intelligence and society as the current popular deep learning models are generally weak in explaining the reasoning process and prediction results. Local Interpretable Model-agnostic Explanation (LIME) is a recent technique that explains the predictions of any classifier faithfully by learning an interpretable model locally around the prediction. However, the sampling operation in the standard implementation of LIME is defective. Perturbed samples are generated from a uniform distribution, ignoring the complicated correlation between features. This paper proposes a novel Modified Perturbed Sampling operation for LIME (MPS-LIME), which is formalized as the clique set construction problem. In image classification, MPS-LIME converts the superpixel image into an undirected graph. Various experiments show that the MPS-LIME explanation of the black-box model achieves much better performance in terms of understandability, fidelity, and efficiency.

arXiv:2003.12255

A Comprehensive Review for Breast Histopathology Image Analysis Using Classical and Deep Neural Networks

Breast cancer is one of the most common and deadliest cancers among women. Since histopathological images contain sufficient phenotypic information, they play an indispensable role in the diagnosis and treatment of breast cancers. To improve the accuracy and objectivity of Breast Histopathological Image Analysis (BHIA), Artificial Neural Network (ANN) approaches are widely used in the segmentation and classification tasks of breast histopathological images. In this review, we present a comprehensive overview of the BHIA techniques based on ANNs. First of all, we categorize the BHIA systems into classical and deep neural networks for in-depth investigation. Then, the relevant studies based on BHIA systems are presented. After that, we analyze the existing models to discover the most suitable algorithms. Finally, publicly accessible datasets, along with their download links, are provided for the convenience of future researchers.

arXiv:2105.01601공식 코드 · Papers with Code

MLP-Mixer: An all-MLP Architecture for Vision

Convolutional Neural Networks (CNNs) are the go-to model for computer vision. Recently, attention-based networks, such as the Vision Transformer, have also become popular. In this paper we show that while convolutions and attention are both sufficient for good performance, neither of them are necessary. We present MLP-Mixer, an architecture based exclusively on multi-layer perceptrons (MLPs). MLP-Mixer contains two types of layers: one with MLPs applied independently to image patches (i.e. "mixing" the per-location features), and one with MLPs applied across patches (i.e. "mixing" spatial information). When trained on large datasets, or with modern regularization schemes, MLP-Mixer attains competitive scores on image classification benchmarks, with pre-training and inference cost comparable to state-of-the-art models. We hope that these results spark further research beyond the realms of well established CNNs and Transformers.

arXiv:2107.09362

Protecting Semantic Segmentation Models by Using Block-wise Image Encryption with Secret Key from Unauthorized Access

Since production-level trained deep neural networks (DNNs) are of a great business value, protecting such DNN models against copyright infringement and unauthorized access is in a rising demand. However, conventional model protection methods focused only the image classification task, and these protection methods were never applied to semantic segmentation although it has an increasing number of applications. In this paper, we propose to protect semantic segmentation models from unauthorized access by utilizing block-wise transformation with a secret key for the first time. Protected models are trained by using transformed images. Experiment results show that the proposed protection method allows rightful users with the correct key to access the model to full capacity and deteriorate the performance for unauthorized users. However, protected models slightly drop the segmentation performance compared to non-protected models.

arXiv:2210.05557공식 코드 · Papers with Code

OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions

The pretrain-finetune paradigm in modern computer vision facilitates the success of self-supervised learning, which tends to achieve better transferability than supervised learning. However, with the availability of massive labeled data, a natural question emerges: how to train a better model with both self and full supervision signals? In this paper, we propose Omni-suPErvised Representation leArning with hierarchical supervisions (OPERA) as a solution. We provide a unified perspective of supervisions from labeled and unlabeled data and propose a unified framework of fully supervised and self-supervised learning. We extract a set of hierarchical proxy representations for each image and impose self and full supervisions on the corresponding proxy representations. Extensive experiments on both convolutional neural networks and vision transformers demonstrate the superiority of OPERA in image classification, segmentation, and object detection. Code is available at: https://github.com/wangck20/OPERA.

arXiv:2211.02419

High-Resolution Boundary Detection for Medical Image Segmentation with Piece-Wise Two-Sample T-Test Augmented Loss

Deep learning methods have contributed substantially to the rapid advancement of medical image segmentation, the quality of which relies on the suitable design of loss functions. Popular loss functions, including the cross-entropy and dice losses, often fall short of boundary detection, thereby limiting high-resolution downstream applications such as automated diagnoses and procedures. We developed a novel loss function that is tailored to reflect the boundary information to enhance the boundary detection. As the contrast between segmentation and background regions along the classification boundary naturally induces heterogeneity over the pixels, we propose the piece-wise two-sample t-test augmented (PTA) loss that is infused with the statistical test for such heterogeneity. We demonstrate the improved boundary detection power of the PTA loss compared to benchmark losses without a t-test component.

arXiv:2301.02240

Skip-Attention: Improving Vision Transformers by Paying Less Attention

This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these operations are highly correlated across layers -- a key redundancy that causes unnecessary computations. Based on this observation, we propose SkipAt, a method to reuse self-attention computation from preceding layers to approximate attention at one or more subsequent layers. To ensure that reusing self-attention blocks across layers does not degrade the performance, we introduce a simple parametric function, which outperforms the baseline transformer's performance while running computationally faster. We show the effectiveness of our method in image classification and self-supervised learning on ImageNet-1K, semantic segmentation on ADE20K, image denoising on SIDD, and video denoising on DAVIS. We achieve improved throughput at the same-or-higher accuracy levels in all these tasks.

arXiv:2311.02709

Benchmarking a Benchmark: How Reliable is MS-COCO?

Benchmark datasets are used to profile and compare algorithms across a variety of tasks, ranging from image classification to segmentation, and also play a large role in image pretraining algorithms. Emphasis is placed on results with little regard to the actual content within the dataset. It is important to question what kind of information is being learned from these datasets and what are the nuances and biases within them. In the following work, Sama-COCO, a re-annotation of MS-COCO, is used to discover potential biases by leveraging a shape analysis pipeline. A model is trained and evaluated on both datasets to examine the impact of different annotation conditions. Results demonstrate that annotation styles are important and that annotation pipelines should closely consider the task of interest. The dataset is made publicly available at https://www.sama.com/sama-coco-dataset/ .

arXiv:2312.10948

A Multimodal Approach for Advanced Pest Detection and Classification

This paper presents a novel multi modal deep learning framework for enhanced agricultural pest detection, combining tiny-BERT's natural language processing with R-CNN and ResNet-18's image processing. Addressing limitations of traditional CNN-based visual methods, this approach integrates textual context for more accurate pest identification. The R-CNN and ResNet-18 integration tackles deep CNN issues like vanishing gradients, while tiny-BERT ensures computational efficiency. Employing ensemble learning with linear regression and random forest models, the framework demonstrates superior discriminate ability, as shown in ROC and AUC analyses. This multi modal approach, blending text and image data, significantly boosts pest detection in agriculture. The study highlights the potential of multi modal deep learning in complex real-world scenarios, suggesting future expansions in diversity of datasets, advanced data augmentation, and cross-modal attention mechanisms to enhance model performance.

arXiv:2408.16008

Novel Methods for Analyzing Cellular Interactions in Deep Learning-Based Image Cytometry: Spatial Interaction Potential and Co-Localization Index

The study presents a novel approach for quantifying cellular interactions in digital pathology using deep learning-based image cytometry. Traditional methods struggle with the diversity and heterogeneity of cells within tissues. To address this, we introduce the Spatial Interaction Potential (SIP) and the Co-Localization Index (CLI), leveraging deep learning classification probabilities. SIP assesses the potential for cell-to-cell interactions, similar to an electric field, while CLI incorporates distances between cells, accounting for dynamic cell movements. Our approach enhances traditional methods, providing a more sophisticated analysis of cellular interactions. We validate SIP and CLI through simulations and apply them to colorectal cancer specimens, demonstrating strong correlations with actual biological data. This innovative method offers significant improvements in understanding cellular interactions and has potential applications in various fields of digital pathology.