PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:1905.10157

On the Learning Dynamics of Two-layer Nonlinear Convolutional Neural Networks

Convolutional neural networks (CNNs) have achieved remarkable performance in various fields, particularly in the domain of computer vision. However, why this architecture works well remains to be a mystery. In this work we move a small step toward understanding the success of CNNs by investigating the learning dynamics of a two-layer nonlinear convolutional neural network over some specific data distributions. Rather than the typical Gaussian assumption for input data distribution, we consider a more realistic setting that each data point (e.g. image) contains a specific pattern determining its class label. Within this setting, we both theoretically and empirically show that some convolutional filters will learn the key patterns in data and the norm of these filters will dominate during the training process with stochastic gradient descent. And with any high probability, when the number of iterations is sufficiently large, the CNN model could obtain 100% accuracy over the considered data distributions. Our experiments demonstrate that for practical image classification tasks our findings still hold to some extent.

arXiv:1905.10622

Beyond Visual Semantics: Exploring the Role of Scene Text in Image Understanding

Images with visual and scene text content are ubiquitous in everyday life. However, current image interpretation systems are mostly limited to using only the visual features, neglecting to leverage the scene text content. In this paper, we propose to jointly use scene text and visual channels for robust semantic interpretation of images. We do not only extract and encode visual and scene text cues, but also model their interplay to generate a contextual joint embedding with richer semantics. The contextual embedding thus generated is applied to retrieval and classification tasks on multimedia images, with scene text content, to demonstrate its effectiveness. In the retrieval framework, we augment our learned text-visual semantic representation with scene text cues, to mitigate vocabulary misses that may have occurred during the semantic embedding. To deal with irrelevant or erroneous recognition of scene text, we also apply query-based attention to our text channel. We show how the multi-channel approach, involving visual semantics and scene text, improves upon state of the art.

arXiv:2001.01213

Prediction of MRI Hardware Failures based on Image Features using Ensemble Learning

In order to ensure trouble-free operation, prediction of hardware failures is essential. This applies especially to medical systems. Our goal is to determine hardware which needs to be exchanged before failing. In this work, we focus on predicting failures of 20-channel Head/Neck coils using image-related measurements. Thus, we aim to solve a classification problem with two classes, normal and broken coil. To solve this problem, we use data of two different levels. One level refers to one-dimensional features per individual coil channel on which we found a fully connected neural network to perform best. The other data level uses matrices which represent the overall coil condition and feeds a different neural network. We stack the predictions of those two networks and train a Random Forest classifier as the ensemble learner. Thus, combining insights of both trained models improves the prediction results and allows us to determine the coil's condition with an F-score of 94.14% and an accuracy of 99.09%.

arXiv:2003.01895

Double Backpropagation for Training Autoencoders against Adversarial Attack

Deep learning, as widely known, is vulnerable to adversarial samples. This paper focuses on the adversarial attack on autoencoders. Safety of the autoencoders (AEs) is important because they are widely used as a compression scheme for data storage and transmission, however, the current autoencoders are easily attacked, i.e., one can slightly modify an input but has totally different codes. The vulnerability is rooted the sensitivity of the autoencoders and to enhance the robustness, we propose to adopt double backpropagation (DBP) to secure autoencoder such as VAE and DRAW. We restrict the gradient from the reconstruction image to the original one so that the autoencoder is not sensitive to trivial perturbation produced by the adversarial attack. After smoothing the gradient by DBP, we further smooth the label by Gaussian Mixture Model (GMM), aiming for accurate and robust classification. We demonstrate in MNIST, CelebA, SVHN that our method leads to a robust autoencoder resistant to attack and a robust classifier able for image transition and immune to adversarial attack if combined with GMM.

arXiv:2008.09152

ImagiFilter: A resource to enable the semi-automatic mining of images at scale

Datasets (semi-)automatically collected from the web can easily scale to millions of entries, but a dataset's usefulness is directly related to how clean and high-quality its examples are. In this paper, we describe and publicly release an image dataset along with pretrained models designed to (semi-)automatically filter out undesirable images from very large image collections, possibly obtained from the web. Our dataset focusses on photographic and/or natural images, a very common use-case in computer vision research. We provide annotations for coarse prediction, i.e. photographic vs. non-photographic, and smaller fine-grained prediction tasks where we further break down the non-photographic class into five classes: maps, drawings, graphs, icons, and sketches. Results on held out validation data show that a model architecture with reduced memory footprint achieves over 96% accuracy on coarse-prediction. Our best model achieves 88% accuracy on the hardest fine-grained classification task available. Dataset and pretrained models are available at: https://github.com/houda96/imagi-filter.

arXiv:2103.16241

Improving robustness against common corruptions with frequency biased models

CNNs perform remarkably well when the training and test distributions are i.i.d, but unseen image corruptions can cause a surprisingly large drop in performance. In various real scenarios, unexpected distortions, such as random noise, compression artefacts, or weather distortions are common phenomena. Improving performance on corrupted images must not result in degraded i.i.d performance - a challenge faced by many state-of-the-art robust approaches. Image corruption types have different characteristics in the frequency spectrum and would benefit from a targeted type of data augmentation, which, however, is often unknown during training. In this paper, we introduce a mixture of two expert models specializing in high and low-frequency robustness, respectively. Moreover, we propose a new regularization scheme that minimizes the total variation (TV) of convolution feature-maps to increase high-frequency robustness. The approach improves on corrupted images without degrading in-distribution performance. We demonstrate this on ImageNet-C and also for real-world corruptions on an automotive dataset, both for object classification and object detection.

arXiv:2208.11375

Deep Joint Source-Channel Coding Based on Semantics of Pixels

The semantic information of the image for intelligent tasks is hidden behind the pixels, and slight changes in the pixels will affect the performance of intelligent tasks. In order to preserve semantic information behind pixels for intelligent tasks during wireless image transmission, we propose a joint source-channel coding method based on semantics of pixels, which can improve the performance of intelligent tasks for images at the receiver by retaining semantic information. Specifically, we first utilize gradients of intelligent task's perception results with respect to pixels to represent the semantic importance of pixels. Then, we extract the semantic distortion, and train the deep joint source-channel coding network with the goal of minimizing semantic distortion rather than pixel's distortion. Experiment results demonstrate that the proposed method improves the performance of the intelligent classification task by 1.38% and 66% compared with the SOTA deep joint source-channel coding method and the traditional separately source-channel coding method at the same transmission ra te and signal-to-noise ratio.

arXiv:2211.05565

Computer Vision on X-ray Data in Industrial Production and Security Applications: A Comprehensive Survey

X-ray imaging technology has been used for decades in clinical tasks to reveal the internal condition of different organs, and in recent years, it has become more common in other areas such as industry, security, and geography. The recent development of computer vision and machine learning techniques has also made it easier to automatically process X-ray images and several machine learning-based object (anomaly) detection, classification, and segmentation methods have been recently employed in X-ray image analysis. Due to the high potential of deep learning in related image processing applications, it has been used in most of the studies. This survey reviews the recent research on using computer vision and machine learning for X-ray analysis in industrial production and security applications and covers the applications, techniques, evaluation metrics, datasets, and performance comparison of those techniques on publicly available datasets. We also highlight some drawbacks in the published research and give recommendations for future research in computer vision-based X-ray analysis.

arXiv:2211.06641공식 코드 · Papers with Code

Prediction of Geometric Transformation on Cardiac MRI via Convolutional Neural Network

In the field of medical image, deep convolutional neural networks(ConvNets) have achieved great success in the classification, segmentation, and registration tasks thanks to their unparalleled capacity to learn image features. However, these tasks often require large amounts of manually annotated data and are labor-intensive. Therefore, it is of significant importance for us to study unsupervised semantic feature learning tasks. In our work, we propose to learn features in medical images by training ConvNets to recognize the geometric transformation applied to images and present a simple self-supervised task that can easily predict the geometric transformation. We precisely define a set of geometric transformations in mathematical terms and generalize this model to 3D, taking into account the distinction between spatial and time dimensions. We evaluated our self-supervised method on CMR images of different modalities (bSSFP, T2, LGE) and achieved accuracies of 96.4%, 97.5%, and 96.4%, respectively. The code and models of our paper will be published on: https://github.com/gaoxin492/Geometric_Transformation_CMR

arXiv:2305.08509공식 코드 · Papers with Code

Component-aware anomaly detection framework for adjustable and logical industrial visual inspection

Industrial visual inspection aims at detecting surface defects in products during the manufacturing process. Although existing anomaly detection models have shown great performance on many public benchmarks, their limited adjustability and ability to detect logical anomalies hinder their broader use in real-world settings. To this end, in this paper, we propose a novel component-aware anomaly detection framework (ComAD) which can simultaneously achieve adjustable and logical anomaly detection for industrial scenarios. Specifically, we propose to segment images into multiple components based on a lightweight and nearly training-free unsupervised semantic segmentation model. Then, we design an interpretable logical anomaly detection model through modeling the metrological features of each component and their relationships. Despite its simplicity, our framework achieves state-of-the-art performance on image-level logical anomaly detection. Meanwhile, segmenting a product image into multiple components provides a novel perspective for industrial visual inspection, demonstrating great potential in model customization, noise resistance, and anomaly classification. The code will be available at https://github.com/liutongkun/ComAD.

arXiv:2307.08506

Does Visual Pretraining Help End-to-End Reasoning?

We aim to investigate whether end-to-end learning of visual reasoning can be achieved with general-purpose neural networks, with the help of visual pretraining. A positive result would refute the common belief that explicit visual abstraction (e.g. object detection) is essential for compositional generalization on visual reasoning, and confirm the feasibility of a neural network "generalist" to solve visual recognition and reasoning tasks. We propose a simple and general self-supervised framework which "compresses" each video frame into a small set of tokens with a transformer network, and reconstructs the remaining frames based on the compressed temporal context. To minimize the reconstruction loss, the network must learn a compact representation for each image, as well as capture temporal dynamics and object permanence from temporal context. We perform evaluation on two visual reasoning benchmarks, CATER and ACRE. We observe that pretraining is essential to achieve compositional generalization for end-to-end visual reasoning. Our proposed framework outperforms traditional supervised pretraining, including image classification and explicit object detection, by large margins.

arXiv:2311.17901

SODA: Bottleneck Diffusion Models for Representation Learning

We introduce SODA, a self-supervised diffusion model, designed for representation learning. The model incorporates an image encoder, which distills a source view into a compact representation, that, in turn, guides the generation of related novel views. We show that by imposing a tight bottleneck between the encoder and a denoising decoder, and leveraging novel view synthesis as a self-supervised objective, we can turn diffusion models into strong representation learners, capable of capturing visual semantics in an unsupervised manner. To the best of our knowledge, SODA is the first diffusion model to succeed at ImageNet linear-probe classification, and, at the same time, it accomplishes reconstruction, editing and synthesis tasks across a wide range of datasets. Further investigation reveals the disentangled nature of its emergent latent space, that serves as an effective interface to control and manipulate the model's produced images. All in all, we aim to shed light on the exciting and promising potential of diffusion models, not only for image generation, but also for learning rich and robust representations.

arXiv:2406.15329

An End-to-End, Segmentation-Free, Arabic Handwritten Recognition Model on KHATT

An end-to-end, segmentation-free, deep learning model trained from scratch is proposed, leveraging DCNN for feature extraction, alongside Bidirectional Long-Short Term Memory (BLSTM) for sequence recognition and Connectionist Temporal Classification (CTC) loss function on the KHATT database. The training phase yields remarkable results 84% recognition rate on the test dataset at the character level and 71% on the word level, establishing an image-based sequence recognition framework that operates without segmentation only at the line level. The analysis and preprocessing of the KFUPM Handwritten Arabic TexT (KHATT) database are also presented. Finally, advanced image processing techniques, including filtering, transformation, and line segmentation are implemented. The importance of this work is highlighted by its wide-ranging applications. Including digitizing, documentation, archiving, and text translation in fields such as banking. Moreover, AHR serves as a pivotal tool for making images searchable, enhancing information retrieval capabilities, and enabling effortless editing. This functionality significantly reduces the time and effort required for tasks such as Arabic data organization and manipulation.

arXiv:2504.08544공식 코드 · Papers with Code

Slicing the Gaussian Mixture Wasserstein Distance

Gaussian mixture models (GMMs) are widely used in machine learning for tasks such as clustering, classification, image reconstruction, and generative modeling. A key challenge in working with GMMs is defining a computationally efficient and geometrically meaningful metric. The mixture Wasserstein (MW) distance adapts the Wasserstein metric to GMMs and has been applied in various domains, including domain adaptation, dataset comparison, and reinforcement learning. However, its high computational cost -- arising from repeated Wasserstein distance computations involving matrix square root estimations and an expensive linear program -- limits its scalability to high-dimensional and large-scale problems. To address this, we propose multiple novel slicing-based approximations to the MW distance that significantly reduce computational complexity while preserving key optimal transport properties. From a theoretical viewpoint, we establish several weak and strong equivalences between the introduced metrics, and show the relations to the original MW distance and the well-established sliced Wasserstein distance. Furthermore, we validate the effectiveness of our approach through numerical experiments, demonstrating computational efficiency and applications in clustering, perceptual image comparison, and GMM minimization

arXiv:2507.12760

Unified Medical Image Segmentation with State Space Modeling Snake

Unified Medical Image Segmentation (UMIS) is critical for comprehensive anatomical assessment but faces challenges due to multi-scale structural heterogeneity. Conventional pixel-based approaches, lacking object-level anatomical insight and inter-organ relational modeling, struggle with morphological complexity and feature conflicts, limiting their efficacy in UMIS. We propose Mamba Snake, a novel deep snake framework enhanced by state space modeling for UMIS. Mamba Snake frames multi-contour evolution as a hierarchical state space atlas, effectively modeling macroscopic inter-organ topological relationships and microscopic contour refinements. We introduce a snake-specific vision state space module, the Mamba Evolution Block (MEB), which leverages effective spatiotemporal information aggregation for adaptive refinement of complex morphologies. Energy map shape priors further ensure robust long-range contour evolution in heterogeneous data. Additionally, a dual-classification synergy mechanism is incorporated to concurrently optimize detection and segmentation, mitigating under-segmentation of microstructures in UMIS. Extensive evaluations across five clinical datasets reveal Mamba Snake's superior performance, with an average Dice improvement of 3\% over state-of-the-art methods.

arXiv:2506.23532v2cs.CV

GViT: Representing Images as Gaussians for Visual Recognition

We introduce GViT, a supervised classification framework that uses patch-conditioned 2D Gaussian primitives as input tokens for ViT backbones. A ViT-S-sized encoder predicts each primitive's position, scale, orientation, color, and opacity in one forward pass. The same parameters are constrained to reconstruct the image through a differentiable renderer, as well as serve as classifier inputs. During training, classifier-gradient guidance shapes primitive geometry and appearance under an image reconstruction constraint. On ImageNet-1K, GViT-B achieves 76.9% top-1 accuracy, compared with 79.8% for ViT-B/16 trained with the same recipe. Gaussian tokens also provide explicit spatial support for explanation maps. Grad-CAM over Gaussians improves on patch-based Grad-CAM in segmentation and token-deletion probes, while other probe comparisons are comparable to a ViT. A covariance-based foreground diagnostic on the PASCAL VOC segmentation task further measures the geometry learned through supervised guidance. These results establish the feasibility of recognition from renderable Gaussian parameters and characterize how task supervision shapes this inspectable representation.

arXiv:1310.5619

Devnagari Handwritten Numeral Recognition using Geometric Features and Statistical Combination Classifier

This paper presents a Devnagari Numerical recognition method based on statistical discriminant functions. 17 geometric features based on pixel connectivity, lines, line directions, holes, image area, perimeter, eccentricity, solidity, orientation etc. are used for representing the numerals. Five discriminant functions viz. Linear, Quadratic, Diaglinear, Diagquadratic and Mahalanobis distance are used for classification. 1500 handwritten numerals are used for training. Another 1500 handwritten numerals are used for testing. Experimental results show that Linear, Quadratic and Mahalanobis discriminant functions provide better results. Results of these three Discriminants are fed to a majority voting type Combination classifier. It is found that Combination classifier offers better results over individual classifiers.

arXiv:1811.06992

Image Classification at Supercomputer Scale

Deep learning is extremely computationally intensive, and hardware vendors have responded by building faster accelerators in large clusters. Training deep learning models at petaFLOPS scale requires overcoming both algorithmic and systems software challenges. In this paper, we discuss three systems-related optimizations: (1) distributed batch normalization to control per-replica batch sizes, (2) input pipeline optimizations to sustain model throughput, and (3) 2-D torus all-reduce to speed up gradient summation. We combine these optimizations to train ResNet-50 on ImageNet to 76.3% accuracy in 2.2 minutes on a 1024-chip TPU v3 Pod with a training throughput of over 1.05 million images/second and no accuracy drop.

arXiv:1910.04940

Blink: Fast and Generic Collectives for Distributed ML

Model parameter synchronization across GPUs introduces high overheads for data-parallel training at scale. Existing parameter synchronization protocols cannot effectively leverage available network resources in the face of ever increasing hardware heterogeneity. To address this, we propose Blink, a collective communication library that dynamically generates optimal communication primitives by packing spanning trees. We propose techniques to minimize the number of trees generated and extend Blink to leverage heterogeneous communication channels for faster data transfers. Evaluations show that compared to the state-of-the-art (NCCL), Blink can achieve up to 8x faster model synchronization, and reduce end-to-end training time for image classification tasks by up to 40%.

arXiv:2007.02209

On Connections between Regularizations for Improving DNN Robustness

This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view. Specifically, we study possible connections between several effective methods, including input-gradient regularization, Jacobian regularization, curvature regularization, and a cross-Lipschitz functional. We investigate them on DNNs with general rectified linear activations, which constitute one of the most prevalent families of models for image classification and a host of other machine learning applications. We shed light on essential ingredients of these regularizations and re-interpret their functionality. Through the lens of our study, more principled and efficient regularizations can possibly be invented in the near future.