PyTorchKR Papers

“Image Classification”

총 17,593편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2007.01243공식 코드 · Papers with Code

Learning ordered pooling weights in image classification

Spatial pooling is an important step in computer vision systems like Convolutional Neural Networks or the Bag-of-Words method. The spatial pooling purpose is to combine neighbouring descriptors to obtain a single descriptor for a given region (local or global). The resultant combined vector must be as discriminant as possible, in other words, must contain relevant information, while removing irrelevant and confusing details. Maximum and average are the most common aggregation functions used in the pooling step. To improve the aggregation of relevant information without degrading their discriminative power for image classification, we introduce a simple but effective scheme based on Ordered Weighted Average (OWA) aggregation operators. We present a method to learn the weights of the OWA aggregation operator in a Bag-of-Words framework and in Convolutional Neural Networks, and provide an extensive evaluation showing that OWA based pooling outperforms classical aggregation operators.

arXiv:2110.11499공식 코드 · Papers with Code

Wav2CLIP: Learning Robust Audio Representations From CLIP

We propose Wav2CLIP, a robust audio representation learning method by distilling from Contrastive Language-Image Pre-training (CLIP). We systematically evaluate Wav2CLIP on a variety of audio tasks including classification, retrieval, and generation, and show that Wav2CLIP can outperform several publicly available pre-trained audio representation algorithms. Wav2CLIP projects audio into a shared embedding space with images and text, which enables multimodal applications such as zero-shot classification, and cross-modal retrieval. Furthermore, Wav2CLIP needs just ~10% of the data to achieve competitive performance on downstream tasks compared with fully supervised models, and is more efficient to pre-train than competing methods as it does not require learning a visual model in concert with an auditory model. Finally, we demonstrate image generation from Wav2CLIP as qualitative assessment of the shared embedding space. Our code and model weights are open sourced and made available for further applications.

arXiv:2310.08315

Fusion framework and multimodality for the Laplacian approximation of Bayesian neural networks

This paper considers the problem of sequential fusion of predictions from neural networks (NN) and fusion of predictions from multiple NN. This fusion strategy increases the robustness, i.e., reduces the impact of one incorrect classification and detection of outliers the \nn has not seen during training. This paper uses Laplacian approximation of Bayesian NNs (BNNs) to quantify the uncertainty necessary for fusion. Here, an extension is proposed such that the prediction of the NN can be represented by multimodal distributions. Regarding calibration of the estimated uncertainty in the prediction, the performance is significantly improved by having the flexibility to represent a multimodal distribution. Two class classical image classification tasks, i.e., MNIST and CFAR10, and image sequences from camera traps of carnivores in Swedish forests have been used to demonstrate the fusion strategies and proposed extension to the Laplacian approximation.

arXiv:2505.14049공식 코드 · Papers with Code

Learning Concept-Driven Logical Rules for Interpretable and Generalizable Medical Image Classification

The pursuit of decision safety in clinical applications highlights the potential of concept-based methods in medical imaging. While these models offer active interpretability, they often suffer from concept leakages, where unintended information within soft concept representations undermines both interpretability and generalizability. Moreover, most concept-based models focus solely on local explanations (instance-level), neglecting the global decision logic (dataset-level). To address these limitations, we propose Concept Rule Learner (CRL), a novel framework to learn Boolean logical rules from binarized visual concepts. CRL employs logical layers to capture concept correlations and extract clinically meaningful rules, thereby providing both local and global interpretability. Experiments on two medical image classification tasks show that CRL achieves competitive performance with existing methods while significantly improving generalizability to out-of-distribution data. The code of our work is available at https://github.com/obiyoag/crl.

arXiv:2611.03078v1eess.IV

Cross-Layer Refinement and Frequency-aware Fusion Network for Multi-Source Remote Sensing Image Classification

Multi-source remote sensing image classification benefits from complementary spectral and structural information. However, identifying discriminative cross-modal features remains challenging. This letter proposes a Cross-Layer Refinement and Frequency-aware Fusion Network (CRFNet) within a lightweight dual-branch architecture. Specifically, a Cross-Layer Refinement Attention (CLRA) module propagates selected attention relationships across successive layers and employs top relation selection to progressively strengthen discriminative spatial dependencies while suppressing irrelevant responses. Furthermore, a Frequency-aware Complementary Fusion (FCF) module combines frequency-wise interactions with cross-modal channel attention in the Fourier domain. The resulting representations are then converted into spatial-domain gates to selectively modulate complementary features. Experiments on the Houston 2013 and Augsburg datasets demonstrate that the proposed CRFNet consistently outperforms several state-of-the-art methods. The codes are publicly available at https://github.com/oucailab/CRFNet

arXiv:1701.06643

Residual and Plain Convolutional Neural Networks for 3D Brain MRI Classification

In the recent years there have been a number of studies that applied deep learning algorithms to neuroimaging data. Pipelines used in those studies mostly require multiple processing steps for feature extraction, although modern advancements in deep learning for image classification can provide a powerful framework for automatic feature generation and more straightforward analysis. In this paper, we show how similar performance can be achieved skipping these feature extraction steps with the residual and plain 3D convolutional neural network architectures. We demonstrate the performance of the proposed approach for classification of Alzheimer's disease versus mild cognitive impairment and normal controls on the Alzheimer's Disease National Initiative (ADNI) dataset of 3D structural MRI brain scans.

arXiv:2107.03250공식 코드 · Papers with Code

Understanding Intrinsic Robustness Using Label Uncertainty

A fundamental question in adversarial machine learning is whether a robust classifier exists for a given task. A line of research has made some progress towards this goal by studying the concentration of measure, but we argue standard concentration fails to fully characterize the intrinsic robustness of a classification problem since it ignores data labels which are essential to any classification task. Building on a novel definition of label uncertainty, we empirically demonstrate that error regions induced by state-of-the-art models tend to have much higher label uncertainty than randomly-selected subsets. This observation motivates us to adapt a concentration estimation algorithm to account for label uncertainty, resulting in more accurate intrinsic robustness measures for benchmark image classification problems.

arXiv:1607.04942

Sparse Representation-Based Classification: Orthogonal Least Squares or Orthogonal Matching Pursuit?

Spare representation of signals has received significant attention in recent years. Based on these developments, a sparse representation-based classification (SRC) has been proposed for a variety of classification and related tasks, including face recognition. Recently, a class dependent variant of SRC was proposed to overcome the limitations of SRC for remote sensing image classification. Traditionally, greedy pursuit based method such as orthogonal matching pursuit (OMP) are used for sparse coefficient recovery due to their simplicity as well as low time-complexity. However, orthogonal least square (OLS) has not yet been widely used in classifiers that exploit the sparse representation properties of data. Since OLS produces lower signal reconstruction error than OMP under similar conditions, we hypothesize that more accurate signal estimation will further improve the classification performance of classifiers that exploiting the sparsity of data. In this paper, we present a classification method based on OLS, which implements OLS in a classwise manner to perform the classification. We also develop and present its kernelized variant to handle nonlinearly separable data. Based on two real-world benchmarking hyperspectral datasets, we demonstrate that class dependent OLS based methods outperform several baseline methods including traditional SRC and the support vector machine classifier.

논문 ID: document/1014018

Ensemble learning for alcoholism classification using EEG signals

Excessive drinking is a major risk factor that leads to many health complications. The diagnosis of alcoholism is challenging, especially when the standard diagnostic tests rely on blood tests and questionnaires that are subjective to the patient and the examiner. The study’s major goal is to find new electroencephalography (EEG) classification methods to improve past findings and construct a robust EEG classification algorithm to generate accurate predictions with explainable results. The EEG records were examined from two different perspectives and combined with an ensemble of classification models. The first approach was temporal data, and the second was images derived from the original signals. Using fast Fourier transform (FFT) and independent component analysis (ICA), we convert 64-channel temporal data into images along with applying the Symbolic Aggregate approXimation (SAX) technique. Our model combines input data in tabular, temporal, and image formats with an ensemble of linear neural networks, long short-term memory (LSTM), and efficient-net classification models. We have evaluated our method using a publicly available dataset for EEG classification of alcoholic and nonalcoholic subjects. Overall, our algorithm’s highest cross-validation classification accuracy is 85.52% compared to the state-of-the-art EEG-NET’s accuracy of 81.19%

arXiv:1805.07253

Recognition of Activities from Eye Gaze and Egocentric Video

This paper presents a framework for recognition of human activity from egocentric video and eye tracking data obtained from a head-mounted eye tracker. Three channels of information such as eye movement, ego-motion, and visual features are combined for the classification of activities. Image features were extracted using a pre-trained convolutional neural network. Eye and ego-motion are quantized, and the windowed histograms are used as the features. The combination of features obtains better accuracy for activity classification as compared to individual features.

arXiv:2402.00909

Generalizing GradCAM for Embedding Networks

Visualizing CNN is an important part in building trust and explaining model's prediction. Methods like CAM and GradCAM have been really successful in localizing area of the image responsible for the output but are only limited to classification models. In this paper, we present a new method EmbeddingCAM, which generalizes the Grad-CAM for embedding networks. We show that for classification networks, EmbeddingCAM reduces to GradCAM. We show the effectiveness of our method on CUB-200-2011 dataset and also present quantitative and qualitative analysis on the dataset.

arXiv:2501.06389

Kolmogorov-Arnold networks for metal surface defect classification

This paper presents the application of Kolmogorov-Arnold Networks (KAN) in classifying metal surface defects. Specifically, steel surfaces are analyzed to detect defects such as cracks, inclusions, patches, pitted surfaces, and scratches. Drawing on the Kolmogorov-Arnold theorem, KAN provides a novel approach compared to conventional multilayer perceptrons (MLPs), facilitating more efficient function approximation by utilizing spline functions. The results show that KAN networks can achieve better accuracy than convolutional neural networks (CNNs) with fewer parameters, resulting in faster convergence and improved performance in image classification.

arXiv:2004.01426

Disassembling Object Representations without Labels

In this paper, we study a new representation-learning task, which we termed as disassembling object representations. Given an image featuring multiple objects, the goal of disassembling is to acquire a latent representation, of which each part corresponds to one category of objects. Disassembling thus finds its application in a wide domain such as image editing and few- or zero-shot learning, as it enables category-specific modularity in the learned representations. To this end, we propose an unsupervised approach to achieving disassembling, named Unsupervised Disassembling Object Representation (UDOR). UDOR follows a double auto-encoder architecture, in which a fuzzy classification and an object-removing operation are imposed. The fuzzy classification constrains each part of the latent representation to encode features of up to one object category, while the object-removing, combined with a generative adversarial network, enforces the modularity of the representations and integrity of the reconstructed image. Furthermore, we devise two metrics to respectively measure the modularity of disassembled representations and the visual integrity of reconstructed images. Experimental results demonstrate that the proposed UDOR, despited unsupervised, achieves truly encouraging results on par with those of supervised methods.

arXiv:2007.03844

Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning

Generative Adversarial Networks (GANs) based semi-supervised learning (SSL) approaches are shown to improve classification performance by utilizing a large number of unlabeled samples in conjunction with limited labeled samples. However, their performance still lags behind the state-of-the-art non-GAN based SSL approaches. We identify that the main reason for this is the lack of consistency in class probability predictions on the same image under local perturbations. Following the general literature, we address this issue via label consistency regularization, which enforces the class probability predictions for an input image to be unchanged under various semantic-preserving perturbations. In this work, we introduce consistency regularization into the vanilla semi-GAN to address this critical limitation. In particular, we present a new composite consistency regularization method which, in spirit, leverages both local consistency and interpolation consistency. We demonstrate the efficacy of our approach on two SSL image classification benchmark datasets, SVHN and CIFAR-10. Our experiments show that this new composite consistency regularization based semi-GAN significantly improves its performance and achieves new state-of-the-art performance among GAN-based SSL approaches.

arXiv:2310.05337

What do larger image classifiers memorise?

The success of modern neural networks has prompted study of the connection between memorisation and generalisation: overparameterised models generalise well, despite being able to perfectly fit (memorise) completely random labels. To carefully study this issue, Feldman proposed a metric to quantify the degree of memorisation of individual training examples, and empirically computed the corresponding memorisation profile of a ResNet on image classification bench-marks. While an exciting first glimpse into what real-world models memorise, this leaves open a fundamental question: do larger neural models memorise more? We present a comprehensive empirical analysis of this question on image classification benchmarks. We find that training examples exhibit an unexpectedly diverse set of memorisation trajectories across model sizes: most samples experience decreased memorisation under larger models, while the rest exhibit cap-shaped or increasing memorisation. We show that various proxies for the Feldman memorization score fail to capture these fundamental trends. Lastly, we find that knowledge distillation, an effective and popular model compression technique, tends to inhibit memorisation, while also improving generalisation. Specifically, memorisation is mostly inhibited on examples with increasing memorisation trajectories, thus pointing at how distillation improves generalisation.

arXiv:2502.15895

Directional Gradient Projection for Robust Fine-Tuning of Foundation Models

Robust fine-tuning aims to adapt large foundation models to downstream tasks while preserving their robustness to distribution shifts. Existing methods primarily focus on constraining and projecting current model towards the pre-trained initialization based on the magnitudes between fine-tuned and pre-trained weights, which often require extensive hyper-parameter tuning and can sometimes result in underfitting. In this work, we propose Directional Gradient Projection (DiGraP), a novel layer-wise trainable method that incorporates directional information from gradients to bridge regularization and multi-objective optimization. Besides demonstrating our method on image classification, as another contribution we generalize this area to the multi-modal evaluation settings for robust fine-tuning. Specifically, we first bridge the uni-modal and multi-modal gap by performing analysis on Image Classification reformulated Visual Question Answering (VQA) benchmarks and further categorize ten out-of-distribution (OOD) VQA datasets by distribution shift types and degree (i.e. near versus far OOD). Experimental results show that DiGraP consistently outperforms existing baselines across Image Classfication and VQA tasks with discriminative and generative backbones, improving both in-distribution (ID) generalization and OOD robustness.

arXiv:2505.22701

Frequency-Adaptive Discrete Cosine-ViT-ResNet Architecture for Sparse-Data Vision

A major challenge in rare animal image classification is the scarcity of data, as many species usually have only a small number of labeled samples. To address this challenge, we designed a hybrid deep-learning framework comprising a novel adaptive DCT preprocessing module, ViT-B16 and ResNet50 backbones, and a Bayesian linear classification head. To our knowledge, we are the first to introduce an adaptive frequency-domain selection mechanism that learns optimal low-, mid-, and high-frequency boundaries suited to the subsequent backbones. Our network first captures image frequency-domain cues via this adaptive DCT partitioning. The adaptively filtered frequency features are then fed into ViT-B16 to model global contextual relationships, while ResNet50 concurrently extracts local, multi-scale spatial representations from the original image. A cross-level fusion strategy seamlessly integrates these frequency- and spatial-domain embeddings, and the fused features are passed through a Bayesian linear classifier to output the final category predictions. On our self-built 50-class wildlife dataset, this approach outperforms conventional CNN and fixed-band DCT pipelines, achieving state-of-the-art accuracy under extreme sample scarcity.

arXiv:1510.06093

Content adaptive screen image scaling

This paper proposes an efficient content adaptive screen image scaling scheme for the real-time screen applications like remote desktop and screen sharing. In the proposed screen scaling scheme, a screen content classification step is first introduced to classify the screen image into text and pictorial regions. Afterward, we propose an adaptive shift linear interpolation algorithm to predict the new pixel values with the shift offset adapted to the content type of each pixel. The shift offset for each screen content type is offline optimized by minimizing the theoretical interpolation error based on the training samples respectively. The proposed content adaptive screen image scaling scheme can achieve good visual quality and also keep the low complexity for real-time applications.

arXiv:1606.08572

Diversified Visual Attention Networks for Fine-Grained Object Classification

Fine-grained object classification is a challenging task due to the subtle inter-class difference and large intra-class variation. Recently, visual attention models have been applied to automatically localize the discriminative regions of an image for better capturing critical difference and demonstrated promising performance. However, without consideration of the diversity in attention process, most of existing attention models perform poorly in classifying fine-grained objects. In this paper, we propose a diversified visual attention network (DVAN) to address the problems of fine-grained object classification, which substan- tially relieves the dependency on strongly-supervised information for learning to localize discriminative regions compared with attentionless models. More importantly, DVAN explicitly pursues the diversity of attention and is able to gather discriminative information to the maximal extent. Multiple attention canvases are generated to extract convolutional features for attention. An LSTM recurrent unit is employed to learn the attentiveness and discrimination of attention canvases. The proposed DVAN has the ability to attend the object from coarse to fine granularity, and a dynamic internal representation for classification is built up by incrementally combining the information from different locations and scales of the image. Extensive experiments con- ducted on CUB-2011, Stanford Dogs and Stanford Cars datasets have demonstrated that the proposed diversified visual attention networks achieve competitive performance compared to the state- of-the-art approaches, without using any prior knowledge, user interaction or external resource in training or testing.

arXiv:2306.14119공식 코드 · Papers with Code

SHISRCNet: Super-resolution And Classification Network For Low-resolution Breast Cancer Histopathology Image

The rapid identification and accurate diagnosis of breast cancer, known as the killer of women, have become greatly significant for those patients. Numerous breast cancer histopathological image classification methods have been proposed. But they still suffer from two problems. (1) These methods can only hand high-resolution (HR) images. However, the low-resolution (LR) images are often collected by the digital slide scanner with limited hardware conditions. Compared with HR images, LR images often lose some key features like texture, which deeply affects the accuracy of diagnosis. (2) The existing methods have fixed receptive fields, so they can not extract and fuse multi-scale features well for images with different magnification factors. To fill these gaps, we present a \textbf{S}ingle \textbf{H}istopathological \textbf{I}mage \textbf{S}uper-\textbf{R}esolution \textbf{C}lassification network (SHISRCNet), which consists of two modules: Super-Resolution (SR) and Classification (CF) modules. SR module reconstructs LR images into SR ones. CF module extracts and fuses the multi-scale features of SR images for classification. In the training stage, we introduce HR images into the CF module to enhance SHISRCNet's performance. Finally, through the joint training of these two modules, super-resolution and classified of LR images are integrated into our model. The experimental results demonstrate that the effects of our method are close to the SOTA methods with taking HR images as inputs.