PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2610.03218v1cs.CV

VisionMX: 비전 모델을 위한 마이크로스케일링 사후 학습 양자화 구현

VisionMX: Unlocking Microscaling Post-Training Quantization for Vision Models

마이크로스케일링(Microscaling, MX) 포맷은 효율적인 학습(training) 및 추론(inference)을 위한 하드웨어 지원 접근법으로 주목받고 있습니다. 이 방식은 저정밀도(low-precision) 요소와 공유 블록 스케일을 결합하지만, 비전 모델에 미치는 영향은 아직 충분히 연구되지 않았습니다. 본 연구에서는 다양한 비전 모델 및 작업 전반에 걸쳐 사후 학습(post-training) MX 양자화(quantization)를 체계적으로 조사합니다. 직접 변환에 대한 분석을 통해 세 가지 오차 원인을 확인했습니다. 즉, 블록 스케일 표현, 일부 소형 합성곱 가중치(weight) 텐서와 비균일 요소 그리드 간의 불량한 정렬, 그리고 비음수 활성화 값에 의한 부호 있는 코드의 불충분한 활용입니다. 이러한 발견을 바탕으로, 유계 가중치 반올림(bounded weight rounding)을 최적화하고 활성화 값에 접을 수 있는 아핀 보정(foldable affine correction)을 적용하는 사후 학습 MX 양자화 방법인 VisionMX를 제안합니다. 여러 MX 스타일 포맷을 사용하여 이미지 분류(image classification), 객체 검출(object detection), 시맨틱 분할(semantic segmentation), 저조도 이미지 향상 작업 전반에서 VisionMX를 평가했습니다. VisionMX는 직접 변환 및 평가된 사후 학습 양자화 기준 모델들을 개선하며, MX 변환에 가장 민감한 아키텍처에서 가장 큰 폭의 성능 복구를 달성합니다.

arXiv:1805.08113

Stacked Semantic-Guided Attention Model for Fine-Grained Zero-Shot Learning

Zero-Shot Learning (ZSL) is achieved via aligning the semantic relationships between the global image feature vector and the corresponding class semantic descriptions. However, using the global features to represent fine-grained images may lead to sub-optimal results since they neglect the discriminative differences of local regions. Besides, different regions contain distinct discriminative information. The important regions should contribute more to the prediction. To this end, we propose a novel stacked semantics-guided attention (S2GA) model to obtain semantic relevant features by using individual class semantic features to progressively guide the visual features to generate an attention map for weighting the importance of different local regions. Feeding both the integrated visual features and the class semantic features into a multi-class classification architecture, the proposed framework can be trained end-to-end. Extensive experimental results on CUB and NABird datasets show that the proposed approach has a consistent improvement on both fine-grained zero-shot classification and retrieval tasks.

arXiv:1805.00932

Exploring the Limits of Weakly Supervised Pretraining

State-of-the-art visual perception models for a wide range of tasks rely on supervised pretraining. ImageNet classification is the de facto pretraining task for these models. Yet, ImageNet is now nearly ten years old and is by modern standards "small". Even so, relatively little is known about the behavior of pretraining with datasets that are multiple orders of magnitude larger. The reasons are obvious: such datasets are difficult to collect and annotate. In this paper, we present a unique study of transfer learning with large convolutional networks trained to predict hashtags on billions of social media images. Our experiments demonstrate that training for large-scale hashtag prediction leads to excellent results. We show improvements on several image classification and object detection tasks, and report the highest ImageNet-1k single-crop, top-1 accuracy to date: 85.4% (97.6% top-5). We also perform extensive experiments that provide novel empirical data on the relationship between large-scale pretraining and transfer learning performance.

arXiv:1803.07385

Are you eligible? Predicting adulthood from face images via class specific mean autoencoder

Predicting if a person is an adult or a minor has several applications such as inspecting underage driving, preventing purchase of alcohol and tobacco by minors, and granting restricted access. The challenging nature of this problem arises due to the complex and unique physiological changes that are observed with age progression. This paper presents a novel deep learning based formulation, termed as Class Specific Mean Autoencoder, to learn the intra-class similarity and extract class-specific features. We propose that the feature of a particular class if brought similar/closer to the mean feature of that class can help in learning class-specific representations. The proposed formulation is applied for the task of adulthood classification which predicts whether the given face image is of an adult or not. Experiments are performed on two large databases and the results show that the proposed algorithm yields higher classification accuracy compared to existing algorithms and a Commercial-Off-The-Shelf system.

arXiv:1703.00356

Graph-based Isometry Invariant Representation Learning

Learning transformation invariant representations of visual data is an important problem in computer vision. Deep convolutional networks have demonstrated remarkable results for image and video classification tasks. However, they have achieved only limited success in the classification of images that undergo geometric transformations. In this work we present a novel Transformation Invariant Graph-based Network (TIGraNet), which learns graph-based features that are inherently invariant to isometric transformations such as rotation and translation of input images. In particular, images are represented as signals on graphs, which permits to replace classical convolution and pooling layers in deep networks with graph spectral convolution and dynamic graph pooling layers that together contribute to invariance to isometric transformations. Our experiments show high performance on rotated and translated images from the test set compared to classical architectures that are very sensitive to transformations in the data. The inherent invariance properties of our framework provide key advantages, such as increased resiliency to data variability and sustained performance with limited training sets.

arXiv:1812.07627공식 코드 · Papers with Code

Clustering-Oriented Representation Learning with Attractive-Repulsive Loss

The standard loss function used to train neural network classifiers, categorical cross-entropy (CCE), seeks to maximize accuracy on the training data; building useful representations is not a necessary byproduct of this objective. In this work, we propose clustering-oriented representation learning (COREL) as an alternative to CCE in the context of a generalized attractive-repulsive loss framework. COREL has the consequence of building latent representations that collectively exhibit the quality of natural clustering within the latent space of the final hidden layer, according to a predefined similarity function. Despite being simple to implement, COREL variants outperform or perform equivalently to CCE in a variety of scenarios, including image and news article classification using both feed-forward and convolutional neural networks. Analysis of the latent spaces created with different similarity functions facilitates insights on the different use cases COREL variants can satisfy, where the Cosine-COREL variant makes a consistently clusterable latent space, while Gaussian-COREL consistently obtains better classification accuracy than CCE.

arXiv:2002.09024

MaxUp: A Simple Way to Improve Generalization of Neural Network Training

We propose \emph{MaxUp}, an embarrassingly simple, highly effective technique for improving the generalization performance of machine learning models, especially deep neural networks. The idea is to generate a set of augmented data with some random perturbations or transforms and minimize the maximum, or worst case loss over the augmented data. By doing so, we implicitly introduce a smoothness or robustness regularization against the random perturbations, and hence improve the generation performance. For example, in the case of Gaussian perturbation, \emph{MaxUp} is asymptotically equivalent to using the gradient norm of the loss as a penalty to encourage smoothness. We test \emph{MaxUp} on a range of tasks, including image classification, language modeling, and adversarial certification, on which \emph{MaxUp} consistently outperforms the existing best baseline methods, without introducing substantial computational overhead. In particular, we improve ImageNet classification from the state-of-the-art top-1 accuracy $85.5\%$ without extra data to $85.8\%$. Code will be released soon.

arXiv:2009.01745

GTAdam: Gradient Tracking with Adaptive Momentum for Distributed Online Optimization

This paper deals with a network of computing agents aiming to solve an online optimization problem in a distributed fashion, i.e., by means of local computation and communication, without any central coordinator. We propose the gradient tracking with adaptive momentum estimation (GTAdam) distributed algorithm, which combines a gradient tracking mechanism with first and second order momentum estimates of the gradient. The algorithm is analyzed in the online setting for strongly convex cost functions with Lipschitz continuous gradients. We provide an upper bound for the dynamic regret given by a term related to the initial conditions and another term related to the temporal variations of the objective functions. Moreover, a linear convergence rate is guaranteed in the static setup. The algorithm is tested on a time-varying classification problem, on a (moving) target localization problem, and in a stochastic optimization setup from image classification. In these numerical experiments from multi-agent learning, GTAdam outperforms state-of-the-art distributed optimization methods.

arXiv:2103.07531

Uncertainty-guided Model Generalization to Unseen Domains

We study a worst-case scenario in generalization: Out-of-domain generalization from a single source. The goal is to learn a robust model from a single source and expect it to generalize over many unknown distributions. This challenging problem has been seldom investigated while existing solutions suffer from various limitations. In this paper, we propose a new solution. The key idea is to augment the source capacity in both input and label spaces, while the augmentation is guided by uncertainty assessment. To the best of our knowledge, this is the first work to (1) access the generalization uncertainty from a single source and (2) leverage it to guide both input and label augmentation for robust generalization. The model training and deployment are effectively organized in a Bayesian meta-learning framework. We conduct extensive comparisons and ablation study to validate our approach. The results prove our superior performance in a wide scope of tasks including image classification, semantic segmentation, text classification, and speech recognition.

arXiv:2301.11375공식 코드 · Papers with Code

Neural networks learn to magnify areas near decision boundaries

In machine learning, there is a long history of trying to build neural networks that can learn from fewer example data by baking in strong geometric priors. However, it is not always clear a priori what geometric constraints are appropriate for a given task. Here, we consider the possibility that one can uncover useful geometric inductive biases by studying how training molds the Riemannian geometry induced by unconstrained neural network feature maps. We first show that at infinite width, neural networks with random parameters induce highly symmetric metrics on input space. This symmetry is broken by feature learning: networks trained to perform classification tasks learn to magnify local areas along decision boundaries. This holds in deep networks trained on high-dimensional image classification tasks, and even in self-supervised representation learning. These results begins to elucidate how training shapes the geometry induced by unconstrained neural network feature maps, laying the groundwork for an understanding of this richly nonlinear form of feature learning.

arXiv:2306.07365

Intelligent Multi-channel Meta-imagers for Accelerating Machine Vision

Rapid developments in machine vision have led to advances in a variety of industries, from medical image analysis to autonomous systems. These achievements, however, typically necessitate digital neural networks with heavy computational requirements, which are limited by high energy consumption and further hinder real-time decision-making when computation resources are not accessible. Here, we demonstrate an intelligent meta-imager that is designed to work in concert with a digital back-end to off-load computationally expensive convolution operations into high-speed and low-power optics. In this architecture, metasurfaces enable both angle and polarization multiplexing to create multiple information channels that perform positive and negatively valued convolution operations in a single shot. The meta-imager is employed for object classification, experimentally achieving 98.6% accurate classification of handwritten digits and 88.8% accuracy in classifying fashion images. With compactness, high speed, and low power consumption, this approach could find a wide range of applications in artificial intelligence and machine vision applications.

arXiv:2401.09518

On-Off Pattern Encoding and Path-Count Encoding as Deep Neural Network Representations

Understanding the encoded representation of Deep Neural Networks (DNNs) has been a fundamental yet challenging objective. In this work, we focus on two possible directions for analyzing representations of DNNs by studying simple image classification tasks. Specifically, we consider \textit{On-Off pattern} and \textit{PathCount} for investigating how information is stored in deep representations. On-off pattern of a neuron is decided as `on' or `off' depending on whether the neuron's activation after ReLU is non-zero or zero. PathCount is the number of paths that transmit non-zero energy from the input to a neuron. We investigate how neurons in the network encodes information by replacing each layer's activation with On-Off pattern or PathCount and evaluating its effect on classification performance. We also examine correlation between representation and PathCount. Finally, we show a possible way to improve an existing DNN interpretation method, Class Activation Map (CAM), by directly utilizing On-Off or PathCount.

arXiv:2505.17579

Ownership Verification of DNN Models Using White-Box Adversarial Attacks with Specified Probability Manipulation

In this paper, we propose a novel framework for ownership verification of deep neural network (DNN) models for image classification tasks. It allows verification of model identity by both the rightful owner and third party without presenting the original model. We assume a gray-box scenario where an unauthorized user owns a model that is illegally copied from the original model, provides services in a cloud environment, and the user throws images and receives the classification results as a probability distribution of output classes. The framework applies a white-box adversarial attack to align the output probability of a specific class to a designated value. Due to the knowledge of original model, it enables the owner to generate such adversarial examples. We propose a simple but effective adversarial attack method based on the iterative Fast Gradient Sign Method (FGSM) by introducing control parameters. Experimental results confirm the effectiveness of the identification of DNN models using adversarial attack.

arXiv:2107.08650

Compound Figure Separation of Biomedical Images with Side Loss

Unsupervised learning algorithms (e.g., self-supervised learning, auto-encoder, contrastive learning) allow deep learning models to learn effective image representations from large-scale unlabeled data. In medical image analysis, even unannotated data can be difficult to obtain for individual labs. Fortunately, national-level efforts have been made to provide efficient access to obtain biomedical image data from previous scientific publications. For instance, NIH has launched the Open-i search engine that provides a large-scale image database with free access. However, the images in scientific publications consist of a considerable amount of compound figures with subplots. To extract and curate individual subplots, many different compound figure separation approaches have been developed, especially with the recent advances in deep learning. However, previous approaches typically required resource extensive bounding box annotation to train detection models. In this paper, we propose a simple compound figure separation (SimCFS) framework that uses weak classification annotations from individual images. Our technical contribution is three-fold: (1) we introduce a new side loss that is designed for compound figure separation; (2) we introduce an intra-class image augmentation method to simulate hard cases; (3) the proposed framework enables an efficient deployment to new classes of images, without requiring resource extensive bounding box annotations. From the results, the SimCFS achieved a new state-of-the-art performance on the ImageCLEF 2016 Compound Figure Separation Database. The source code of SimCFS is made publicly available at https://github.com/hrlblab/ImageSeperation.

arXiv:2303.00915공식 코드 · Papers with Code

BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs

Biomedical data is inherently multimodal, comprising physical measurements and natural language narratives. A generalist biomedical AI model needs to simultaneously process different modalities of data, including text and images. Therefore, training an effective generalist biomedical model requires high-quality multimodal data, such as parallel image-text pairs. Here, we present PMC-15M, a novel dataset that is two orders of magnitude larger than existing biomedical multimodal datasets such as MIMIC-CXR, and spans a diverse range of biomedical image types. PMC-15M contains 15 million biomedical image-text pairs collected from 4.4 million scientific articles. Based on PMC-15M, we have pretrained BiomedCLIP, a multimodal foundation model, with domain-specific adaptations tailored to biomedical vision-language processing. We conducted extensive experiments and ablation studies on standard biomedical imaging tasks from retrieval to classification to visual question-answering (VQA). BiomedCLIP achieved new state-of-the-art results in a wide range of standard datasets, substantially outperforming prior approaches. Intriguingly, by large-scale pretraining on diverse biomedical image types, BiomedCLIP even outperforms state-of-the-art radiology-specific models such as BioViL in radiology-specific tasks such as RSNA pneumonia detection. In summary, BiomedCLIP is a fully open-access foundation model that achieves state-of-the-art performance on various biomedical tasks, paving the way for transformative multimodal biomedical discovery and applications. We release our models at https://aka.ms/biomedclip to facilitate future research in multimodal biomedical AI.

arXiv:2403.06288

Probing Image Compression For Class-Incremental Learning

Image compression emerges as a pivotal tool in the efficient handling and transmission of digital images. Its ability to substantially reduce file size not only facilitates enhanced data storage capacity but also potentially brings advantages to the development of continual machine learning (ML) systems, which learn new knowledge incrementally from sequential data. Continual ML systems often rely on storing representative samples, also known as exemplars, within a limited memory constraint to maintain the performance on previously learned data. These methods are known as memory replay-based algorithms and have proven effective at mitigating the detrimental effects of catastrophic forgetting. Nonetheless, the limited memory buffer size often falls short of adequately representing the entire data distribution. In this paper, we explore the use of image compression as a strategy to enhance the buffer's capacity, thereby increasing exemplar diversity. However, directly using compressed exemplars introduces domain shift during continual ML, marked by a discrepancy between compressed training data and uncompressed testing data. Additionally, it is essential to determine the appropriate compression algorithm and select the most effective rate for continual ML systems to balance the trade-off between exemplar quality and quantity. To this end, we introduce a new framework to incorporate image compression for continual ML including a pre-processing data compression step and an efficient compression rate/algorithm selection method. We conduct extensive experiments on CIFAR-100 and ImageNet datasets and show that our method significantly improves image classification accuracy in continual ML settings.

arXiv:2409.04038공식 코드 · Papers with Code

PlantSeg: A Large-Scale In-the-wild Dataset for Plant Disease Segmentation

Plant diseases pose significant threats to agriculture. It necessitates proper diagnosis and effective treatment to safeguard crop yields. To automate the diagnosis process, image segmentation is usually adopted for precisely identifying diseased regions, thereby advancing precision agriculture. Developing robust image segmentation models for plant diseases demands high-quality annotations across numerous images. However, existing plant disease datasets typically lack segmentation labels and are often confined to controlled laboratory settings, which do not adequately reflect the complexity of natural environments. Motivated by this fact, we established PlantSeg, a large-scale segmentation dataset for plant diseases. PlantSeg distinguishes itself from existing datasets in three key aspects. (1) Annotation type: Unlike the majority of existing datasets that only contain class labels or bounding boxes, each image in PlantSeg includes detailed and high-quality segmentation masks, associated with plant types and disease names. (2) Image source: Unlike typical datasets that contain images from laboratory settings, PlantSeg primarily comprises in-the-wild plant disease images. This choice enhances the practical applicability, as the trained models can be applied for integrated disease management. (3) Scale: PlantSeg is extensive, featuring 11,400 images with disease segmentation masks and an additional 8,000 healthy plant images categorized by plant type. Extensive technical experiments validate the high quality of PlantSeg's annotations. This dataset not only allows researchers to evaluate their image classification methods but also provides a critical foundation for developing and benchmarking advanced plant disease segmentation algorithms.

arXiv:2506.02493공식 코드 · Papers with Code

Towards In-the-wild 3D Plane Reconstruction from a Single Image

3D plane reconstruction from a single image is a crucial yet challenging topic in 3D computer vision. Previous state-of-the-art (SOTA) methods have focused on training their system on a single dataset from either indoor or outdoor domain, limiting their generalizability across diverse testing data. In this work, we introduce a novel framework dubbed ZeroPlane, a Transformer-based model targeting zero-shot 3D plane detection and reconstruction from a single image, over diverse domains and environments. To enable data-driven models across multiple domains, we have curated a large-scale planar benchmark, comprising over 14 datasets and 560,000 high-resolution, dense planar annotations for diverse indoor and outdoor scenes. To address the challenge of achieving desirable planar geometry on multi-dataset training, we propose to disentangle the representation of plane normal and offset, and employ an exemplar-guided, classification-then-regression paradigm to learn plane and offset respectively. Additionally, we employ advanced backbones as image encoder, and present an effective pixel-geometry-enhanced plane embedding module to further facilitate planar reconstruction. Extensive experiments across multiple zero-shot evaluation datasets have demonstrated that our approach significantly outperforms previous methods on both reconstruction accuracy and generalizability, especially over in-the-wild data. Our code and data are available at: https://github.com/jcliu0428/ZeroPlane.

arXiv:2205.08390

HoVer-Trans: Anatomy-aware HoVer-Transformer for ROI-free Breast Cancer Diagnosis in Ultrasound Images

Ultrasonography is an important routine examination for breast cancer diagnosis, due to its non-invasive, radiation-free and low-cost properties. However, the diagnostic accuracy of breast cancer is still limited due to its inherent limitations. It would be a tremendous success if we can precisely diagnose breast cancer by breast ultrasound images (BUS). Many learning-based computer-aided diagnostic methods have been proposed to achieve breast cancer diagnosis/lesion classification. However, most of them require a pre-define ROI and then classify the lesion inside the ROI. Conventional classification backbones, such as VGG16 and ResNet50, can achieve promising classification results with no ROI requirement. But these models lack interpretability, thus restricting their use in clinical practice. In this study, we propose a novel ROI-free model for breast cancer diagnosis in ultrasound images with interpretable feature representations. We leverage the anatomical prior knowledge that malignant and benign tumors have different spatial relationships between different tissue layers, and propose a HoVer-Transformer to formulate this prior knowledge. The proposed HoVer-Trans block extracts the inter- and intra-layer spatial information horizontally and vertically. We conduct and release an open dataset GDPH&SYSUCC for breast cancer diagnosis in BUS. The proposed model is evaluated in three datasets by comparing with four CNN-based models and two vision transformer models via five-fold cross validation. It achieves state-of-the-art classification performance with the best model interpretability. In the meanwhile, our proposed model outperforms two senior sonographers on the breast cancer diagnosis when only one BUS image is given.

arXiv:1801.01693

Efficient Image Evidence Analysis of CNN Classification Results

Convolutional neural networks (CNNs) define the current state-of-the-art for image recognition. With their emerging popularity, especially for critical applications like medical image analysis or self-driving cars, confirmability is becoming an issue. The black-box nature of trained predictors make it difficult to trace failure cases or to understand the internal reasoning processes leading to results. In this paper we introduce a novel efficient method to visualise evidence that lead to decisions in CNNs. In contrast to network fixation or saliency map methods, our method is able to illustrate the evidence for or against a classifier's decision in input pixel space approximately 10 times faster than previous methods. We also show that our approach is less prone to noise and can focus on the most relevant input regions, thus making it more accurate and interpretable. Moreover, by making simplifications we link our method with other visualisation methods, providing a general explanation for gradient-based visualisation techniques. We believe that our work makes network introspection more feasible for debugging and understanding deep convolutional networks. This will increase trust between humans and deep learning models.