PyTorchKR Papers

“Image Classification”

총 18,351편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2206.01736

Adaptive Adversarial Training to Improve Adversarial Robustness of DNNs for Medical Image Segmentation and Detection

It is known that Deep Neural networks (DNNs) are vulnerable to adversarial attacks, and the adversarial robustness of DNNs could be improved by adding adversarial noises to training data (e.g., the standard adversarial training (SAT)). However, inappropriate noises added to training data may reduce a model's performance, which is termed the trade-off between accuracy and robustness. This problem has been sufficiently studied for the classification of whole images but has rarely been explored for image analysis tasks in the medical application domain, including image segmentation, landmark detection, and object detection tasks. In this study, we show that, for those medical image analysis tasks, the SAT method has a severe issue that limits its practical use: it generates a fixed and unified level of noise for all training samples for robust DNN training. A high noise level may lead to a large reduction in model performance and a low noise level may not be effective in improving robustness. To resolve this issue, we design an adaptive-margin adversarial training (AMAT) method that generates sample-wise adaptive adversarial noises for robust DNN training. In contrast to the existing, classification-oriented adversarial training methods, our AMAT method uses a loss-defined-margin strategy so that it can be applied to different tasks as long as the loss functions are well-defined. We successfully apply our AMAT method to state-of-the-art DNNs, using five publicly available datasets. The experimental results demonstrate that: (1) our AMAT method can be applied to the three seemingly different tasks in the medical image application domain; (2) AMAT outperforms the SAT method in adversarial robustness; (3) AMAT has a minimal reduction in prediction accuracy on clean data, compared with the SAT method; and (4) AMAT has almost the same training time cost as SAT.

arXiv:2607.15128v1cs.CV

DAPGNet: 초분광 이미지 분류를 위한 동적 적응형 물리 유도 그래프 확산 네트워크

DAPGNet: Dynamic Adaptive Physics-Guided Graph Diffusion Network for Hyperspectral Image Classification

초분광 이미지(HSI) 분류는 스펙트럼 변이, 혼합 픽셀, 이질적 경계 조건에서 신뢰할 수 있는 픽셀 간 관계 모델링을 요구한다. 기존 그래프 기반 HSI 분류기는 보통 공간 근접성, 초픽셀(superpixel) 연결성, 또는 학습된 특징 친화도로부터 그래프 토폴로지를 구성한다. 그러나 연속 밴드가 담고 있는 스펙트럼 물리 사전 정보는 토폴로지 추정과 메시지 전파에 미치는 영향이 제한적이다. 본 논문은 관계 수준의 그래프 학습에 구조 제약 물리 사전 정보를 주입하는 동적 적응형 물리 유도 그래프 확산 네트워크인 DAPGNet을 제안한다. DAPGNet은 먼저 연속적인 스펙트럼 응답을 노드별 다중 스케일 물리 사전 표현으로 인코딩한다. 이어 2단계 그래프 구성기가 스펙트럼-공간 친화도, 물리 사전 일관성, 공간 거리를 결합하여 물리 사전 인식 희소 토폴로지를 형성한다. 그래프 확산 과정에서 학습된 엣지 가중치는 가산적 어텐션 바이어스로 변환되며, 물리 게이트는 그래프 집계 특징과 투영된 물리 사전 특징 사이에서 노드별·특징별 보간을 수행한다. 교차 스케일 융합은 서로 다른 확산 깊이의 노드 상태를 통합하며, 네트워크는 주 분류, 보조 감독, 2차 스펙트럼 평활성 정규화로 최적화된다. Indian Pines, WHU-Hi-LongKou, Houston2013, Houston2018 데이터셋에서의 실험 결과, DAPGNet은 대표적인 CNN-, 트랜스포머-, Mamba-, 그래프 기반 베이스라인 중 OA, AA, Kappa에서 최고 성능을 달성한다. 네 개 데이터셋 전반에서 가장 강력한 경쟁 방법 대비 AA를 3.64~7.31 퍼센트 포인트 향상시킨다. 소거 및 민감도 분석은 물리 사전 추출, 사전 인식 토폴로지 구성, 물리 게이트 전파, 스펙트럼 평활성 정규화의 상호 보완적 효과를 추가로 뒷받침한다.

arXiv:2206.02180

Semi-Supervised Learning for Mars Imagery Classification and Segmentation

With the progress of Mars exploration, numerous Mars image data are collected and need to be analyzed. However, due to the imbalance and distortion of Martian data, the performance of existing computer vision models is unsatisfactory. In this paper, we introduce a semi-supervised framework for machine vision on Mars and try to resolve two specific tasks: classification and segmentation. Contrastive learning is a powerful representation learning technique. However, there is too much information overlap between Martian data samples, leading to a contradiction between contrastive learning and Martian data. Our key idea is to reconcile this contradiction with the help of annotations and further take advantage of unlabeled data to improve performance. For classification, we propose to ignore inner-class pairs on labeled data as well as neglect negative pairs on unlabeled data, forming supervised inter-class contrastive learning and unsupervised similarity learning. For segmentation, we extend supervised inter-class contrastive learning into an element-wise mode and use online pseudo labels for supervision on unlabeled areas. Experimental results show that our learning strategies can improve the classification and segmentation models by a large margin and outperform state-of-the-art approaches.

arXiv:2306.08385공식 코드 · Papers with Code

NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification

Graph neural networks have been extensively studied for learning with inter-connected data. Despite this, recent evidence has revealed GNNs' deficiencies related to over-squashing, heterophily, handling long-range dependencies, edge incompleteness and particularly, the absence of graphs altogether. While a plausible solution is to learn new adaptive topology for message passing, issues concerning quadratic complexity hinder simultaneous guarantees for scalability and precision in large networks. In this paper, we introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes, as an important building block for a pioneering Transformer-style network for node classification on large graphs, dubbed as \textsc{NodeFormer}. Specifically, the efficient computation is enabled by a kernerlized Gumbel-Softmax operator that reduces the algorithmic complexity to linearity w.r.t. node numbers for learning latent graph structures from large, potentially fully-connected graphs in a differentiable manner. We also provide accompanying theory as justification for our design. Extensive experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs (with up to 2M nodes) and graph-enhanced applications (e.g., image classification) where input graphs are missing.

arXiv:2412.11917공식 코드 · Papers with Code

Does VLM Classification Benefit from LLM Description Semantics?

Accurately describing images with text is a foundation of explainable AI. Vision-Language Models (VLMs) like CLIP have recently addressed this by aligning images and texts in a shared embedding space, expressing semantic similarities between vision and language embeddings. VLM classification can be improved with descriptions generated by Large Language Models (LLMs). However, it is difficult to determine the contribution of actual description semantics, as the performance gain may also stem from a semantic-agnostic ensembling effect, where multiple modified text prompts act as a noisy test-time augmentation for the original one. We propose an alternative evaluation scenario to decide if a performance boost of LLM-generated descriptions is caused by such a noise augmentation effect or rather by genuine description semantics. The proposed scenario avoids noisy test-time augmentation and ensures that genuine, distinctive descriptions cause the performance boost. Furthermore, we propose a training-free method for selecting discriminative descriptions that work independently of classname-ensembling effects. Our approach identifies descriptions that effectively differentiate classes within a local CLIP label neighborhood, improving classification accuracy across seven datasets. Additionally, we provide insights into the explainability of description-based image classification with VLMs.

arXiv:1608.08021공식 코드 · Papers with Code

PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection

This paper presents how we can achieve the state-of-the-art accuracy in multi-category object detection task while minimizing the computational cost by adapting and combining recent technical innovations. Following the common pipeline of "CNN feature extraction + region proposal + RoI classification", we mainly redesign the feature extraction part, since region proposal part is not computationally expensive and classification part can be efficiently compressed with common techniques like truncated SVD. Our design principle is "less channels with more layers" and adoption of some building blocks including concatenated ReLU, Inception, and HyperNet. The designed network is deep and thin and trained with the help of batch normalization, residual connections, and learning rate scheduling based on plateau detection. We obtained solid results on well-known object detection benchmarks: 83.8% mAP (mean average precision) on VOC2007 and 82.5% mAP on VOC2012 (2nd place), while taking only 750ms/image on Intel i7-6700K CPU with a single core and 46ms/image on NVIDIA Titan X GPU. Theoretically, our network requires only 12.3% of the computational cost compared to ResNet-101, the winner on VOC2012.

arXiv:1906.12213공식 코드 · Papers with Code

On the notion of number in humans and machines

In this paper, we performed two types of software experiments to study the numerosity classification (subitizing) in humans and machines. Experiments focus on a particular kind of task is referred to as Semantic MNIST or simply SMNIST where the numerosity of objects placed in an image must be determined. The experiments called SMNIST for Humans are intended to measure the capacity of the Object File System in humans. In this type of experiment the measurement result is in well agreement with the value known from the cognitive psychology literature. The experiments called SMNIST for Machines serve similar purposes but they investigate existing, well known (but originally developed for other purpose) and under development deep learning computer programs. These measurement results can be interpreted similar to the results from SMNIST for Humans. The main thesis of this paper can be formulated as follows: in machines the image classification artificial neural networks can learn to distinguish numerosities with better accuracy when these numerosities are smaller than the capacity of OFS in humans. Finally, we outline a conceptual framework to investigate the notion of number in humans and machines.

arXiv:2103.05114

Learning Invariant Representations across Domains and Tasks

Being expensive and time-consuming to collect massive COVID-19 image samples to train deep classification models, transfer learning is a promising approach by transferring knowledge from the abundant typical pneumonia datasets for COVID-19 image classification. However, negative transfer may deteriorate the performance due to the feature distribution divergence between two datasets and task semantic difference in diagnosing pneumonia and COVID-19 that rely on different characteristics. It is even more challenging when the target dataset has no labels available, i.e., unsupervised task transfer learning. In this paper, we propose a novel Task Adaptation Network (TAN) to solve this unsupervised task transfer problem. In addition to learning transferable features via domain-adversarial training, we propose a novel task semantic adaptor that uses the learning-to-learn strategy to adapt the task semantics. Experiments on three public COVID-19 datasets demonstrate that our proposed method achieves superior performance. Especially on COVID-DA dataset, TAN significantly increases the recall and F1 score by 5.0% and 7.8% compared to recently strong baselines. Moreover, we show that TAN also achieves superior performance on several public domain adaptation benchmarks.

arXiv:2204.03206공식 코드 · Papers with Code

L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation

Mining precise class-aware attention maps, a.k.a, class activation maps, is essential for weakly supervised semantic segmentation. In this paper, we present L2G, a simple online local-to-global knowledge transfer framework for high-quality object attention mining. We observe that classification models can discover object regions with more details when replacing the input image with its local patches. Taking this into account, we first leverage a local classification network to extract attentions from multiple local patches randomly cropped from the input image. Then, we utilize a global network to learn complementary attention knowledge across multiple local attention maps online. Our framework conducts the global network to learn the captured rich object detail knowledge from a global view and thereby produces high-quality attention maps that can be directly used as pseudo annotations for semantic segmentation networks. Experiments show that our method attains 72.1% and 44.2% mIoU scores on the validation set of PASCAL VOC 2012 and MS COCO 2014, respectively, setting new state-of-the-art records. Code is available at https://github.com/PengtaoJiang/L2G.

arXiv:2209.06375

Self-Supervised Clustering on Image-Subtracted Data with Deep-Embedded Self-Organizing Map

Developing an effective automatic classifier to separate genuine sources from artifacts is essential for transient follow-ups in wide-field optical surveys. The identification of transient detections from the subtraction artifacts after the image differencing process is a key step in such classifiers, known as real-bogus classification problem. We apply a self-supervised machine learning model, the deep-embedded self-organizing map (DESOM) to this "real-bogus" classification problem. DESOM combines an autoencoder and a self-organizing map to perform clustering in order to distinguish between real and bogus detections, based on their dimensionality-reduced representations. We use 32x32 normalized detection thumbnails as the input of DESOM. We demonstrate different model training approaches, and find that our best DESOM classifier shows a missed detection rate of 6.6% with a false positive rate of 1.5%. DESOM offers a more nuanced way to fine-tune the decision boundary identifying likely real detections when used in combination with other types of classifiers, for example built on neural networks or decision trees. We also discuss other potential usages of DESOM and its limitations.

논문 ID: document/9861684

Local Low-Rank Approximation With Superpixel-Guided Locality Preserving Graph for Hyperspectral Image Classification

Given the detrimental effect of spectral variations in a hyperspectral image (HSI), this article investigates to recover its discriminative representation to improve the classification performance. We propose a new method, namely local low-rank approximation with superpixel-guided locality preserving graph (LLRA-SLPG), which can reduce the spectral variations and preserve the local manifold structure of an HSI. Specifically, the LLRA-SLPG method first clusters pixels of an HSI into several groups (i.e., superpixels). By taking advantage of the local manifold structure, a Laplacian graph is constructed from the superpixels to ensure that a typical pixel should be similar to its neighbors within the same superpixel. The LLRA-SLPG model can increase the compactness of pixels belonging to the same class by reducing spectral variations while promoting local consistency via the Laplacian graph. The objective function of the LLRA-SLPG model can be solved efficiently in an iterative manner. Experimental results on four benchmark datasets validate the superiority of the LLRA-SLPG model over state-of-the-art methods, particularly in cases where only extremely few training pixels are available.

arXiv:2310.03161

Neural architecture impact on identifying temporally extended Reinforcement Learning tasks

Inspired by recent developments in attention models for image classification and natural language processing, we present various Attention based architectures in reinforcement learning (RL) domain, capable of performing well on OpenAI Gym Atari-2600 game suite. In spite of the recent success of Deep Reinforcement learning techniques in various fields like robotics, gaming and healthcare, they suffer from a major drawback that neural networks are difficult to interpret. We try to get around this problem with the help of Attention based models. In Attention based models, extracting and overlaying of attention map onto images allows for direct observation of information used by agent to select actions and easier interpretation of logic behind the chosen actions. Our models in addition to playing well on gym-Atari environments, also provide insights on how agent perceives its environment. In addition, motivated by recent developments in attention based video-classification models using Vision Transformer, we come up with an architecture based on Vision Transformer, for image-based RL domain too. Compared to previous works in Vision Transformer, our model is faster to train and requires fewer computational resources. 3

arXiv:2405.09851공식 코드 · Papers with Code

Region of Interest Detection in Melanocytic Skin Tumor Whole Slide Images -- Nevus & Melanoma

Automated region of interest detection in histopathological image analysis is a challenging and important topic with tremendous potential impact on clinical practice. The deep-learning methods used in computational pathology may help us to reduce costs and increase the speed and accuracy of cancer diagnosis. We started with the UNC Melanocytic Tumor Dataset cohort that contains 160 hematoxylin and eosin whole-slide images of primary melanomas (86) and nevi (74). We randomly assigned 80% (134) as a training set and built an in-house deep-learning method to allow for classification, at the slide level, of nevi and melanomas. The proposed method performed well on the other 20% (26) test dataset; the accuracy of the slide classification task was 92.3% and our model also performed well in terms of predicting the region of interest annotated by the pathologists, showing excellent performance of our model on melanocytic skin tumors. Even though we tested the experiments on the skin tumor dataset, our work could also be extended to other medical image detection problems to benefit the clinical evaluation and diagnosis of different tumors.

arXiv:2405.12705공식 코드 · Papers with Code

Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting

This work addresses the need for a balanced approach between performance and efficiency in scalable production environments for visually-rich document understanding (VDU) tasks. Currently, there is a reliance on large document foundation models that offer advanced capabilities but come with a heavy computational burden. In this paper, we propose a multimodal early exit (EE) model design that incorporates various training strategies, exit layer types and placements. Our goal is to achieve a Pareto-optimal balance between predictive performance and efficiency for multimodal document image classification. Through a comprehensive set of experiments, we compare our approach with traditional exit policies and showcase an improved performance-efficiency trade-off. Our multimodal EE design preserves the model's predictive capabilities, enhancing both speed and latency. This is achieved through a reduction of over 20% in latency, while fully retaining the baseline accuracy. This research represents the first exploration of multimodal EE design within the VDU community, highlighting as well the effectiveness of calibration in improving confidence scores for exiting at different layers. Overall, our findings contribute to practical VDU applications by enhancing both performance and efficiency.

arXiv:1707.04585공식 코드 · Papers with Code

The Reversible Residual Network: Backpropagation Without Storing Activations

Deep residual networks (ResNets) have significantly pushed forward the state-of-the-art on image classification, increasing in performance as networks grow both deeper and wider. However, memory consumption becomes a bottleneck, as one needs to store the activations in order to calculate gradients using backpropagation. We present the Reversible Residual Network (RevNet), a variant of ResNets where each layer's activations can be reconstructed exactly from the next layer's. Therefore, the activations for most layers need not be stored in memory during backpropagation. We demonstrate the effectiveness of RevNets on CIFAR-10, CIFAR-100, and ImageNet, establishing nearly identical classification accuracy to equally-sized ResNets, even though the activation storage requirements are independent of depth.

arXiv:1402.2013

Foreground segmentation based on multi-resolution and matting

We propose a foreground segmentation algorithm that does foreground extraction under different scales and refines the result by matting. First, the input image is filtered and resampled to 5 different resolutions. Then each of them is segmented by adaptive figure-ground classification and the best segmentation is automatically selected by an evaluation score that maximizes the difference between foreground and background. This segmentation is upsampled to the original size, and a corresponding trimap is built. Closed-form matting is employed to label the boundary region, and the result is refined by a final figure-ground classification. Experiments show the success of our method in treating challenging images with cluttered background and adapting to loose initial bounding-box.

arXiv:1908.07086

Human uncertainty makes classification more robust

The classification performance of deep neural networks has begun to asymptote at near-perfect levels. However, their ability to generalize outside the training set and their robustness to adversarial attacks have not. In this paper, we make progress on this problem by training with full label distributions that reflect human perceptual uncertainty. We first present a new benchmark dataset which we call CIFAR10H, containing a full distribution of human labels for each image of the CIFAR10 test set. We then show that, while contemporary classifiers fail to exhibit human-like uncertainty on their own, explicit training on our dataset closes this gap, supports improved generalization to increasingly out-of-training-distribution test datasets, and confers robustness to adversarial attacks.

arXiv:2202.07952

TimeREISE: Time-series Randomized Evolving Input Sample Explanation

Deep neural networks are one of the most successful classifiers across different domains. However, due to their limitations concerning interpretability their use is limited in safety critical context. The research field of explainable artificial intelligence addresses this problem. However, most of the interpretability methods are aligned to the image modality by design. The paper introduces TimeREISE a model agnostic attribution method specifically aligned to success in the context of time series classification. The method shows superior performance compared to existing approaches concerning different well-established measurements. TimeREISE is applicable to any time series classification network, its runtime does not scale in a linear manner concerning the input shape and it does not rely on prior data knowledge.

arXiv:2311.01111공식 코드 · Papers with Code

H-NeXt: The next step towards roto-translation invariant networks

The widespread popularity of equivariant networks underscores the significance of parameter efficient models and effective use of training data. At a time when robustness to unseen deformations is becoming increasingly important, we present H-NeXt, which bridges the gap between equivariance and invariance. H-NeXt is a parameter-efficient roto-translation invariant network that is trained without a single augmented image in the training set. Our network comprises three components: an equivariant backbone for learning roto-translation independent features, an invariant pooling layer for discarding roto-translation information, and a classification layer. H-NeXt outperforms the state of the art in classification on unaugmented training sets and augmented test sets of MNIST and CIFAR-10.

arXiv:1911.11010

Event Recognition with Automatic Album Detection based on Sequential Processing, Neural Attention and Image Captioning

In this paper a new formulation of event recognition task is examined: it is required to predict event categories in a gallery of images, for which albums (groups of photos corresponding to a single event) are unknown. We propose the novel two-stage approach. At first, features are extracted in each photo using the pre-trained convolutional neural network. These features are classified individually. The scores of the classifier are used to group sequential photos into several clusters. Finally, the features of photos in each group are aggregated into a single descriptor using neural attention mechanism. This algorithm is optionally extended to improve the accuracy for classification of each image in an album. In contrast to conventional fine-tuning of convolutional neural networks (CNN) we proposed to use image captioning, i.e., generative model that converts images to textual descriptions. They are one-hot encoded and summarized into sparse feature vector suitable for learning of arbitrary classifier. Experimental study with Photo Event Collection and Multi-Label Curation of Flickr Events Dataset demonstrates that our approach is 9-20% more accurate than event recognition on single photos. Moreover, proposed method has 13-16% lower error rate than classification of groups of photos obtained with hierarchical clustering. It is experimentally shown that the image captions trained on Conceptual Captions dataset can be classified more accurately than the features from object detector, though they both are obviously not as rich as the CNN-based features. However, it is possible to combine our approach with conventional CNNs in an ensemble to provide the state-of-the-art results for several event datasets.