PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2101.11453공식 코드 · Papers with Code

Meta Adversarial Training against Universal Patches

Recently demonstrated physical-world adversarial attacks have exposed vulnerabilities in perception systems that pose severe risks for safety-critical applications such as autonomous driving. These attacks place adversarial artifacts in the physical world that indirectly cause the addition of a universal patch to inputs of a model that can fool it in a variety of contexts. Adversarial training is the most effective defense against image-dependent adversarial attacks. However, tailoring adversarial training to universal patches is computationally expensive since the optimal universal patch depends on the model weights which change during training. We propose meta adversarial training (MAT), a novel combination of adversarial training with meta-learning, which overcomes this challenge by meta-learning universal patches along with model training. MAT requires little extra computation while continuously adapting a large set of patches to the current model. MAT considerably increases robustness against universal patch attacks on image classification and traffic-light detection.

arXiv:2102.06164

Sample Efficient Learning of Image-Based Diagnostic Classifiers Using Probabilistic Labels

Deep learning approaches often require huge datasets to achieve good generalization. This complicates its use in tasks like image-based medical diagnosis, where the small training datasets are usually insufficient to learn appropriate data representations. For such sensitive tasks it is also important to provide the confidence in the predictions. Here, we propose a way to learn and use probabilistic labels to train accurate and calibrated deep networks from relatively small datasets. We observe gains of up to 22% in the accuracy of models trained with these labels, as compared with traditional approaches, in three classification tasks: diagnosis of hip dysplasia, fatty liver, and glaucoma. The outputs of models trained with probabilistic labels are calibrated, allowing the interpretation of its predictions as proper probabilities. We anticipate this approach will apply to other tasks where few training instances are available and expert knowledge can be encoded as probabilities.

arXiv:2105.03341공식 코드 · Papers with Code

Exploring Instance Relations for Unsupervised Feature Embedding

Despite the great progress achieved in unsupervised feature embedding, existing contrastive learning methods typically pursue view-invariant representations through attracting positive sample pairs and repelling negative sample pairs in the embedding space, while neglecting to systematically explore instance relations. In this paper, we explore instance relations including intra-instance multi-view relation and inter-instance interpolation relation for unsupervised feature embedding. Specifically, we embed intra-instance multi-view relation by aligning the distribution of the distance between an instance's different augmented samples and negative samples. We explore inter-instance interpolation relation by transferring the ratio of information for image sample interpolation from pixel space to feature embedding space. The proposed approach, referred to as EIR, is simple-yet-effective and can be easily inserted into existing view-invariant contrastive learning based methods. Experiments conducted on public benchmarks for image classification and retrieval report state-of-the-art or comparable performance.

arXiv:2110.13950

Can't Fool Me: Adversarially Robust Transformer for Video Understanding

Deep neural networks have been shown to perform poorly on adversarial examples. To address this, several techniques have been proposed to increase robustness of a model for image classification tasks. However, in video understanding tasks, developing adversarially robust models is still unexplored. In this paper, we aim to bridge this gap. We first show that simple extensions of image based adversarially robust models slightly improve the worst-case performance. Further, we propose a temporal attention regularization scheme in Transformer to improve the robustness of attention modules to adversarial examples. We illustrate using a large-scale video data set YouTube-8M that the final model (A-ART) achieves close to non-adversarial performance on its adversarial example set. We achieve 91% GAP on adversarial examples, whereas baseline Transformer and simple adversarial extensions achieve 72.9% and 82% respectively, showing significant improvement in robustness over the state-of-the-art.

arXiv:2111.08701

Interpretability Aware Model Training to Improve Robustness against Out-of-Distribution Magnetic Resonance Images in Alzheimer's Disease Classification

Owing to its pristine soft-tissue contrast and high resolution, structural magnetic resonance imaging (MRI) is widely applied in neurology, making it a valuable data source for image-based machine learning (ML) and deep learning applications. The physical nature of MRI acquisition and reconstruction, however, causes variations in image intensity, resolution, and signal-to-noise ratio. Since ML models are sensitive to such variations, performance on out-of-distribution data, which is inherent to the setting of a deployed healthcare ML application, typically drops below acceptable levels. We propose an interpretability aware adversarial training regime to improve robustness against out-of-distribution samples originating from different MRI hardware. The approach is applied to 1.5T and 3T MRIs obtained from the Alzheimer's Disease Neuroimaging Initiative database. We present preliminary results showing promising performance on out-of-distribution samples.

arXiv:2405.07166공식 코드 · Papers with Code

Resource Efficient Perception for Vision Systems

Despite the rapid advancement in the field of image recognition, the processing of high-resolution imagery remains a computational challenge. However, this processing is pivotal for extracting detailed object insights in areas ranging from autonomous vehicle navigation to medical imaging analyses. Our study introduces a framework aimed at mitigating these challenges by leveraging memory efficient patch based processing for high resolution images. It incorporates a global context representation alongside local patch information, enabling a comprehensive understanding of the image content. In contrast to traditional training methods which are limited by memory constraints, our method enables training of ultra high resolution images. We demonstrate the effectiveness of our method through superior performance on 7 different benchmarks across classification, object detection, and segmentation. Notably, the proposed method achieves strong performance even on resource-constrained devices like Jetson Nano. Our code is available at https://github.com/Visual-Conception-Group/Localized-Perception-Constrained-Vision-Systems.

arXiv:2407.08151

Enrich the content of the image Using Context-Aware Copy Paste

Data augmentation remains a widely utilized technique in deep learning, particularly in tasks such as image classification, semantic segmentation, and object detection. Among them, Copy-Paste is a simple yet effective method and gain great attention recently. However, existing Copy-Paste often overlook contextual relevance between source and target images, resulting in inconsistencies in generated outputs. To address this challenge, we propose a context-aware approach that integrates Bidirectional Latent Information Propagation (BLIP) for content extraction from source images. By matching extracted content information with category information, our method ensures cohesive integration of target objects using Segment Anything Model (SAM) and You Only Look Once (YOLO). This approach eliminates the need for manual annotation, offering an automated and user-friendly solution. Experimental evaluations across diverse datasets demonstrate the effectiveness of our method in enhancing data diversity and generating high-quality pseudo-images across various computer vision tasks.

arXiv:2411.02697

Transferable polychromatic optical encoder for neural networks

Artificial neural networks (ANNs) have fundamentally transformed the field of computer vision, providing unprecedented performance. However, these ANNs for image processing demand substantial computational resources, often hindering real-time operation. In this paper, we demonstrate an optical encoder that can perform convolution simultaneously in three color channels during the image capture, effectively implementing several initial convolutional layers of a ANN. Such an optical encoding results in ~24,000 times reduction in computational operations, with a state-of-the art classification accuracy (~73.2%) in free-space optical system. In addition, our analog optical encoder, trained for CIFAR-10 data, can be transferred to the ImageNet subset, High-10, without any modifications, and still exhibits moderate accuracy. Our results evidence the potential of hybrid optical/digital computer vision system in which the optical frontend can pre-process an ambient scene to reduce the energy and latency of the whole computer vision system.

arXiv:2411.14834

Evaluating the Robustness of the "Ensemble Everything Everywhere" Defense

Ensemble everything everywhere is a defense to adversarial examples that was recently proposed to make image classifiers robust. This defense works by ensembling a model's intermediate representations at multiple noisy image resolutions, producing a single robust classification. This defense was shown to be effective against multiple state-of-the-art attacks. Perhaps even more convincingly, it was shown that the model's gradients are perceptually aligned: attacks against the model produce noise that perceptually resembles the targeted class. In this short note, we show that this defense is not robust to adversarial attack. We first show that the defense's randomness and ensembling method cause severe gradient masking. We then use standard adaptive attack techniques to reduce the defense's robust accuracy from 48% to 14% on CIFAR-100 and from 62% to 11% on CIFAR-10, under the $\ell_\infty$-norm threat model with $\varepsilon=8/255$.

arXiv:2608.24142v1cs.CV

프롬프트 학습은 무엇을 바꾸는가? - 비전-언어 모델의 자연어 개념 분석

What Does Prompt Learning Change? -A Natural-Language Concept Analysis of Vision-Language Models

프롬프트 학습은 연속적인 프롬프트 벡터를 최적화하여 CLIP과 같은 비전-언어 모델을 적응시키지만, 학습된 프롬프트는 자연어로 해석하기 어렵다. 본 논문은 각 클래스 조건 텍스트 임베딩을 고정된 자연어 사전의 개념들의 희소 조합으로 표현하는 사후(post-hoc) 방법인 PromptSpLiCE를 제안한다. 프롬프트 학습 전후에 동일한 사전을 사용하면 개념 프로필의 변화를 비교할 수 있다. 대표적인 프롬프트 학습 방법인 CoOp에 대해 11개 이미지 분류 데이터셋에서 PromptSpLiCE를 평가하였다. 개념 프로필은 상당히 변한다. 평균적으로 초기 상위 10개 개념 중 학습 후에도 상위 10에 남는 것은 1.6개에 불과하다. 데이터셋 전반에 걸쳐 프로필 변화는 정확도 향상과 양의 상관관계를 보인다. 또한 현재 프롬프트와 구별되는 이미지 정렬(image-aligned) 개념 방향이 더 큰 손실 민감도를 가질 수 있는 이유에 대한 기하학적 직관을 제공하는 국소 그래디언트 식을 도출한다.

arXiv:2103.13318

Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types

Transfer learning enables to re-use knowledge learned on a source task to help learning a target task. A simple form of transfer learning is common in current state-of-the-art computer vision models, i.e. pre-training a model for image classification on the ILSVRC dataset, and then fine-tune on any target task. However, previous systematic studies of transfer learning have been limited and the circumstances in which it is expected to work are not fully understood. In this paper we carry out an extensive experimental exploration of transfer learning across vastly different image domains (consumer photos, autonomous driving, aerial imagery, underwater, indoor scenes, synthetic, close-ups) and task types (semantic segmentation, object detection, depth estimation, keypoint detection). Importantly, these are all complex, structured output tasks types relevant to modern computer vision applications. In total we carry out over 2000 transfer learning experiments, including many where the source and target come from different image domains, task types, or both. We systematically analyze these experiments to understand the impact of image domain, task type, and dataset size on transfer learning performance. Our study leads to several insights and concrete recommendations: (1) for most tasks there exists a source which significantly outperforms ILSVRC'12 pre-training; (2) the image domain is the most important factor for achieving positive transfer; (3) the source dataset should \emph{include} the image domain of the target dataset to achieve best results; (4) at the same time, we observe only small negative effects when the image domain of the source task is much broader than that of the target; (5) transfer across task types can be beneficial, but its success is heavily dependent on both the source and target task types.

arXiv:1812.11006

TOP-GAN: Label-Free Cancer Cell Classification Using Deep Learning with a Small Training Set

We propose a new deep learning approach for medical imaging that copes with the problem of a small training set, the main bottleneck of deep learning, and apply it for classification of healthy and cancer cells acquired by quantitative phase imaging. The proposed method, called transferring of pre-trained generative adversarial network (TOP-GAN), is a hybridization between transfer learning and generative adversarial networks (GANs). Healthy cells and cancer cells of different metastatic potential have been imaged by low-coherence off-axis holography. After the acquisition, the optical path delay maps of the cells have been extracted and directly used as an input to the deep networks. In order to cope with the small number of classified images, we have used GANs to train a large number of unclassified images from another cell type (sperm cells). After this preliminary training, and after transforming the last layer of the network with new ones, we have designed an automatic classifier for the correct cell type (healthy/primary cancer/metastatic cancer) with 90-99% accuracy, although small training sets of down to several images have been used. These results are better in comparison to other classic methods that aim at coping with the same problem of a small training set. We believe that our approach makes the combination of holographic microscopy and deep learning networks more accessible to the medical field by enabling a rapid, automatic and accurate classification in stain-free imaging flow cytometry. Furthermore, our approach is expected to be applicable to many other medical image classification tasks, suffering from a small training set.

arXiv:1907.00374

Fooling a Real Car with Adversarial Traffic Signs

The attacks on the neural-network-based classifiers using adversarial images have gained a lot of attention recently. An adversary can purposely generate an image that is indistinguishable from a innocent image for a human being but is incorrectly classified by the neural networks. The adversarial images do not need to be tuned to a particular architecture of the classifier - an image that fools one network can fool another one with a certain success rate.The published works mostly concentrate on the use of modified image files for attacks against the classifiers trained on the model databases. Although there exists a general understanding that such attacks can be carried in the real world as well, the works considering the real-world attacks are scarce. Moreover, to the best of our knowledge, there have been no reports on the attacks against real production-grade image classification systems.In our work we present a robust pipeline for reproducible production of adversarial traffic signs that can fool a wide range of classifiers, both open-source and production-grade in the real world. The efficiency of the attacks was checked both with the neural-network-based classifiers and legacy computer vision systems. Most of the attacks have been performed in the black-box mode, e.g. the adversarial signs produced for a particular classifier were used to attack a variety of other classifiers. The efficiency was confirmed in drive-by experiments with a production-grade traffic sign recognition systems of a real car.

arXiv:2003.09152공식 코드 · Papers with Code

Exploring Categorical Regularization for Domain Adaptive Object Detection

In this paper, we tackle the domain adaptive object detection problem, where the main challenge lies in significant domain gaps between source and target domains. Previous work seeks to plainly align image-level and instance-level shifts to eventually minimize the domain discrepancy. However, they still overlook to match crucial image regions and important instances across domains, which will strongly affect domain shift mitigation. In this work, we propose a simple but effective categorical regularization framework for alleviating this issue. It can be applied as a plug-and-play component on a series of Domain Adaptive Faster R-CNN methods which are prominent for dealing with domain adaptive detection. Specifically, by integrating an image-level multi-label classifier upon the detection backbone, we can obtain the sparse but crucial image regions corresponding to categorical information, thanks to the weakly localization ability of the classification manner. Meanwhile, at the instance level, we leverage the categorical consistency between image-level predictions (by the classifier) and instance-level predictions (by the detection head) as a regularization factor to automatically hunt for the hard aligned instances of target domains. Extensive experiments of various domain shift scenarios show that our method obtains a significant performance gain over original Domain Adaptive Faster R-CNN detectors. Furthermore, qualitative visualization and analyses can demonstrate the ability of our method for attending on the key regions/instances targeting on domain adaptation. Our code is open-source and available at \url{https://github.com/Megvii-Nanjing/CR-DA-DET}.

arXiv:2311.10389

Two-Factor Authentication Approach Based on Behavior Patterns for Defeating Puppet Attacks

Fingerprint traits are widely recognized for their unique qualities and security benefits. Despite their extensive use, fingerprint features can be vulnerable to puppet attacks, where attackers manipulate a reluctant but genuine user into completing the authentication process. Defending against such attacks is challenging due to the coexistence of a legitimate identity and an illegitimate intent. In this paper, we propose PUPGUARD, a solution designed to guard against puppet attacks. This method is based on user behavioral patterns, specifically, the user needs to press the capture device twice successively with different fingers during the authentication process. PUPGUARD leverages both the image features of fingerprints and the timing characteristics of the pressing intervals to establish two-factor authentication. More specifically, after extracting image features and timing characteristics, and performing feature selection on the image features, PUPGUARD fuses these two features into a one-dimensional feature vector, and feeds it into a one-class classifier to obtain the classification result. This two-factor authentication method emphasizes dynamic behavioral patterns during the authentication process, thereby enhancing security against puppet attacks. To assess PUPGUARD's effectiveness, we conducted experiments on datasets collected from 31 subjects, including image features and timing characteristics. Our experimental results demonstrate that PUPGUARD achieves an impressive accuracy rate of 97.87% and a remarkably low false positive rate (FPR) of 1.89%. Furthermore, we conducted comparative experiments to validate the superiority of combining image features and timing characteristics within PUPGUARD for enhancing resistance against puppet attacks.

arXiv:2503.09370

Revisiting Medical Image Retrieval via Knowledge Consolidation

As artificial intelligence and digital medicine increasingly permeate healthcare systems, robust governance frameworks are essential to ensure ethical, secure, and effective implementation. In this context, medical image retrieval becomes a critical component of clinical data management, playing a vital role in decision-making and safeguarding patient information. Existing methods usually learn hash functions using bottleneck features, which fail to produce representative hash codes from blended embeddings. Although contrastive hashing has shown superior performance, current approaches often treat image retrieval as a classification task, using category labels to create positive/negative pairs. Moreover, many methods fail to address the out-of-distribution (OOD) issue when models encounter external OOD queries or adversarial attacks. In this work, we propose a novel method to consolidate knowledge of hierarchical features and optimisation functions. We formulate the knowledge consolidation by introducing Depth-aware Representation Fusion (DaRF) and Structure-aware Contrastive Hashing (SCH). DaRF adaptively integrates shallow and deep representations into blended features, and SCH incorporates image fingerprints to enhance the adaptability of positive/negative pairings. These blended features further facilitate OOD detection and content-based recommendation, contributing to a secure AI-driven healthcare environment. Moreover, we present a content-guided ranking to improve the robustness and reproducibility of retrieval results. Our comprehensive assessments demonstrate that the proposed method could effectively recognise OOD samples and significantly outperform existing approaches in medical image retrieval (p<0.05). In particular, our method achieves a 5.6-38.9% improvement in mean Average Precision on the anatomical radiology dataset.

arXiv:2610.40284v1cs.CV

LoRe-MIM: Lost-or-Replaced Masked Image Modeling for Self-Supervised Representation Learning in Whole-Body PET/CT

Deep learning models for whole-body positron emission tomography/computed tomography (PET/CT) hold significant clinical potential for disease detection, treatment planning, and response assessment. However, the time and cost associated with expert annotations remain major bottlenecks in developing robust and generalizable models. Although self-supervised learning (SSL) has emerged as a promising approach to mitigating annotation scarcity, its application to whole-body PET/CT remains relatively underexplored due to the limited availability of large-scale datasets and the challenges associated with learning complementary cross-modal representations. To address these limitations, we curate a heterogeneous, multi-tracer, multi-institutional cohort comprising 6,531 whole-body PET/CT scans and propose LoRe-MIM (Lost-Or-Replaced Masked Image Modelling), a novel self-supervised framework designed to learn multimodal representations through masked image reconstruction. Specifically, LoRe-MIM introduces a masking strategy in which image regions are either replaced with zeros (Lost) or substituted with corresponding complementary imaging modality (Replaced), encouraging the model to capture both modality-specific characteristics and cross-modal relationships. We evaluate the learned representations across multiple downstream tasks, including multimodal PET/CT image reconstruction, patch-based classification into cancer vs. non-cancer, whole-body lesion segmentation, label-efficient training, and robustness assessment. Experimental results demonstrate that LoRe-MIM consistently outperforms the corresponding state-of-the-art baselines across these tasks, highlighting its potential as a scalable and generalizable self-supervised learning framework for whole-body PET/CT analysis.

arXiv:1912.03991

Naive Gabor Networks for Hyperspectral Image Classification

Recently, many convolutional neural network (CNN) methods have been designed for hyperspectral image (HSI) classification since CNNs are able to produce good representations of data, which greatly benefits from a huge number of parameters. However, solving such a high-dimensional optimization problem often requires a large amount of training samples in order to avoid overfitting. Additionally, it is a typical non-convex problem affected by many local minima and flat regions. To address these problems, in this paper, we introduce naive Gabor Networks or Gabor-Nets which, for the first time in the literature, design and learn CNN kernels strictly in the form of Gabor filters, aiming to reduce the number of involved parameters and constrain the solution space, and hence improve the performances of CNNs. Specifically, we develop an innovative phase-induced Gabor kernel, which is trickily designed to perform the Gabor feature learning via a linear combination of local low-frequency and high-frequency components of data controlled by the kernel phase. With the phase-induced Gabor kernel, the proposed Gabor-Nets gains the ability to automatically adapt to the local harmonic characteristics of the HSI data and thus yields more representative harmonic features. Also, this kernel can fulfill the traditional complex-valued Gabor filtering in a real-valued manner, hence making Gabor-Nets easily perform in a usual CNN thread. We evaluated our newly developed Gabor-Nets on three well-known HSIs, suggesting that our proposed Gabor-Nets can significantly improve the performance of CNNs, particularly with a small training set.

arXiv:2103.14977

On the benefits of robust models in modulation recognition

Given the rapid changes in telecommunication systems and their higher dependence on artificial intelligence, it is increasingly important to have models that can perform well under different, possibly adverse, conditions. Deep Neural Networks (DNNs) using convolutional layers are state-of-the-art in many tasks in communications. However, in other domains, like image classification, DNNs have been shown to be vulnerable to adversarial perturbations, which consist of imperceptible crafted noise that when added to the data fools the model into misclassification. This puts into question the security of DNNs in communication tasks, and in particular in modulation recognition. We propose a novel framework to test the robustness of current state-of-the-art models where the adversarial perturbation strength is dependent on the signal strength and measured with the "signal to perturbation ratio" (SPR). We show that current state-of-the-art models are susceptible to these perturbations. In contrast to current research on the topic of image classification, modulation recognition allows us to have easily accessible insights on the usefulness of the features learned by DNNs by looking at the constellation space. When analyzing these vulnerable models we found that adversarial perturbations do not shift the symbols towards the nearest classes in constellation space. This shows that DNNs do not base their decisions on signal statistics that are important for the Bayes-optimal modulation recognition model, but spurious correlations in the training data. Our feature analysis and proposed framework can help in the task of finding better models for communication systems.

arXiv:2202.02382

Fully Automated Tree Topology Estimation and Artery-Vein Classification

We present a fully automatic, graph-based technique for extracting the retinal vascular topology -- that is, how different vessels are connected to each other -- given a single color fundus image. Determining this connectivity is very challenging because vessels cross each other in a 2D image, obscuring their true paths. We quantitatively validated the usefulness of our extraction method by using it to achieve comparable state-of-the-art results in retinal artery-vein classification. Our proposed approach works as follows: We first segment the retinal vessels using our previously developed state-of-the-art segmentation method. Then, we estimate an initial graph from the extracted vessels and assign the most likely blood flow to each edge. We then use a handful of high-level operations (HLOs) to fix errors in the graph. These HLOs include detaching neighboring nodes, shifting the endpoints of an edge, and reversing the estimated blood flow direction for a branch. We use a novel cost function to find the optimal set of HLO operations for a given graph. Finally, we show that our extracted vascular structure is correct by propagating artery/vein labels along the branches. As our experiments show, our topology-based artery-vein labeling achieved state-of-the-art results on three datasets: DRIVE, AV-WIDE, and INSPIRE. We also performed several ablation studies to separately verify the importance of the segmentation and AV labeling steps of our proposed method. These ablation studies further confirmed that our graph extraction pipeline correctly models the underlying vascular anatomy.