PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2505.23386

VModA: An Effective Framework for Adaptive NSFW Image Moderation

Not Safe/Suitable for Work (NSFW) content is rampant on social networks and poses serious harm to citizens, especially minors. Current detection methods mainly rely on deep learning-based image recognition and classification. However, NSFW images are now presented in increasingly sophisticated ways, often using image details and complex semantics to obscure their true nature or attract more views. Although still understandable to humans, these images often evade existing detection methods, posing a significant threat. Further complicating the issue, varying regulations across platforms and regions create additional challenges for effective moderation, leading to detection bias and reduced accuracy. To address this, we propose VModA, a general and effective framework that adapts to diverse moderation rules and handles complex, semantically rich NSFW content across categories. Experimental results show that VModA significantly outperforms existing methods, achieving up to a 54.3% accuracy improvement across NSFW types, including those with complex semantics. Further experiments demonstrate that our method exhibits strong adaptability across categories, scenarios, and base VLMs. We also identified inconsistent and controversial label samples in public NSFW benchmark datasets, re-annotated them, and submitted corrections to the original maintainers. Two datasets have confirmed the updates so far. Additionally, we evaluate VModA in real-world scenarios to demonstrate its practical effectiveness.

arXiv:1801.04271

Comparative Study on Generative Adversarial Networks

In recent years, there have been tremendous advancements in the field of machine learning. These advancements have been made through both academic as well as industrial research. Lately, a fair amount of research has been dedicated to the usage of generative models in the field of computer vision and image classification. These generative models have been popularized through a new framework called Generative Adversarial Networks. Moreover, many modified versions of this framework have been proposed in the last two years. We study the original model proposed by Goodfellow et al. as well as modifications over the original model and provide a comparative analysis of these models.

arXiv:1712.00967

Leaf Identification Using a Deep Convolutional Neural Network

Convolutional neural networks (CNNs) have become popular especially in computer vision in the last few years because they achieved outstanding performance on different tasks, such as image classifications. We propose a nine-layer CNN for leaf identification using the famous Flavia and Foliage datasets. Usually the supervised learning of deep CNNs requires huge datasets for training. However, the used datasets contain only a few examples per plant species. Therefore, we apply data augmentation and transfer learning to prevent our network from overfitting. The trained CNNs achieve recognition rates above 99% on the Flavia and Foliage datasets, and slightly outperform current methods for leaf classification.

arXiv:1704.02665공식 코드 · Papers with Code

Supervised Infinite Feature Selection

In this paper, we present a new feature selection method that is suitable for both unsupervised and supervised problems. We build upon the recently proposed Infinite Feature Selection (IFS) method where feature subsets of all sizes (including infinity) are considered. We extend IFS in two ways. First, we propose a supervised version of it. Second, we propose new ways of forming the feature adjacency matrix that perform better for unsupervised problems. We extensively evaluate our methods on many benchmark datasets, including large image-classification datasets (PASCAL VOC), and show that our methods outperform both the IFS and the widely used "minimum-redundancy maximum-relevancy (mRMR)" feature selection algorithm.

arXiv:1505.02982

Automatic Script Identification in the Wild

With the rapid increase of transnational communication and cooperation, people frequently encounter multilingual scenarios in various situations. In this paper, we are concerned with a relatively new problem: script identification at word or line levels in natural scenes. A large-scale dataset with a great quantity of natural images and 10 types of widely used languages is constructed and released. In allusion to the challenges in script identification in real-world scenarios, a deep learning based algorithm is proposed. The experiments on the proposed dataset demonstrate that our algorithm achieves superior performance, compared with conventional image classification methods, such as the original CNN architecture and LLC.

arXiv:1811.03549

An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images

Fully-connected Conditional Random Field (CRF) is often used as post-processing to refine voxel classification results by encouraging spatial coherence. In this paper, we propose a new end-to-end training method called Posterior-CRF. In contrast with previous approaches which use the original image intensity in the CRF, our approach applies 3D, fully connected CRF to the posterior probabilities from a CNN and optimizes both CNN and CRF together. The experiments on white matter hyperintensities segmentation demonstrate that our method outperforms CNN, post-processing CRF and different end-to-end training CRF approaches.

arXiv:1903.04064

Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation

In this work, we connect two distinct concepts for unsupervised domain adaptation: feature distribution alignment between domains by utilizing the task-specific decision boundary and the Wasserstein metric. Our proposed sliced Wasserstein discrepancy (SWD) is designed to capture the natural notion of dissimilarity between the outputs of task-specific classifiers. It provides a geometrically meaningful guidance to detect target samples that are far from the support of the source and enables efficient distribution alignment in an end-to-end trainable fashion. In the experiments, we validate the effectiveness and genericness of our method on digit and sign recognition, image classification, semantic segmentation, and object detection.

arXiv:1909.12473공식 코드 · Papers with Code

Noisy Batch Active Learning with Deterministic Annealing

We study the problem of training machine learning models incrementally with batches of samples annotated with noisy oracles. We select each batch of samples that are important and also diverse via clustering and importance sampling. More importantly, we incorporate model uncertainty into the sampling probability to compensate for poor estimation of the importance scores when the training data is too small to build a meaningful model. Experiments on benchmark image classification datasets (MNIST, SVHN, CIFAR10, and EMNIST) show improvement over existing active learning strategies. We introduce an extra denoising layer to deep networks to make active learning robust to label noises and show significant improvements.

arXiv:2105.10142

Safety Metrics for Semantic Segmentation in Autonomous Driving

Within the context of autonomous driving, safety-related metrics for deep neural networks have been widely studied for image classification and object detection. In this paper, we further consider safety-aware correctness and robustness metrics specialized for semantic segmentation. The novelty of our proposal is to move beyond pixel-level metrics: Given two images with each having N pixels being class-flipped, the designed metrics should, depending on the clustering of pixels being class-flipped or the location of occurrence, reflect a different level of safety criticality. The result evaluated on an autonomous driving dataset demonstrates the validity and practicality of our proposed methodology.

arXiv:2311.11853

Asynchronous Bioplausible Neuron for SNN for Event Vision

Spiking Neural Networks (SNNs) offer a biologically inspired approach to computer vision that can lead to more efficient processing of visual data with reduced energy consumption. However, maintaining homeostasis within these networks is challenging, as it requires continuous adjustment of neural responses to preserve equilibrium and optimal processing efficiency amidst diverse and often unpredictable input signals. In response to these challenges, we propose the Asynchronous Bioplausible Neuron (ABN), a dynamic spike firing mechanism to auto-adjust the variations in the input signal. Comprehensive evaluation across various datasets demonstrates ABN's enhanced performance in image classification and segmentation, maintenance of neural equilibrium, and energy efficiency.

arXiv:2406.15918

DISentangled Counterfactual Visual interpretER (DISCOVER) generalizes to natural images

We recently presented DISentangled COunterfactual Visual interpretER (DISCOVER), a method toward systematic visual interpretability of image-based classification models and demonstrated its applicability to two biomedical domains. Here we demonstrate that DISCOVER can be applied to the domain of natural images. First, DISCOVER visually interpreted the nose size, the muzzle area, and the face size as semantic discriminative visual traits discriminating between facial images of dogs versus cats. Second, DISCOVER visually interpreted the cheeks and jawline, eyebrows and hair, and the eyes, as discriminative facial characteristics. These successful visual interpretations across two natural images domains indicate that DISCOVER is a generalized interpretability method.

arXiv:2302.09682

Dual Attention Model with Reinforcement Learning for Classification of Histology Whole-Slide Images

Digital whole slide images (WSIs) are generally captured at microscopic resolution and encompass extensive spatial data. Directly feeding these images to deep learning models is computationally intractable due to memory constraints, while downsampling the WSIs risks incurring information loss. Alternatively, splitting the WSIs into smaller patches may result in a loss of important contextual information. In this paper, we propose a novel dual attention approach, consisting of two main components, both inspired by the visual examination process of a pathologist: The first soft attention model processes a low magnification view of the WSI to identify relevant regions of interest, followed by a custom sampling method to extract diverse and spatially distinct image tiles from the selected ROIs. The second component, the hard attention classification model further extracts a sequence of multi-resolution glimpses from each tile for classification. Since hard attention is non-differentiable, we train this component using reinforcement learning to predict the location of the glimpses. This approach allows the model to focus on essential regions instead of processing the entire tile, thereby aligning with a pathologist's way of diagnosis. The two components are trained in an end-to-end fashion using a joint loss function to demonstrate the efficacy of the model. The proposed model was evaluated on two WSI-level classification problems: Human epidermal growth factor receptor 2 scoring on breast cancer histology images and prediction of Intact/Loss status of two Mismatch Repair biomarkers from colorectal cancer histology images. We show that the proposed model achieves performance better than or comparable to the state-of-the-art methods while processing less than 10% of the WSI at the highest magnification and reducing the time required to infer the WSI-level label by more than 75%.

arXiv:1906.01828

A Feature Transfer Enabled Multi-Task Deep Learning Model on Medical Imaging

Object detection, segmentation and classification are three common tasks in medical image analysis. Multi-task deep learning (MTL) tackles these three tasks jointly, which provides several advantages saving computing time and resources and improving robustness against overfitting. However, existing multitask deep models start with each task as an individual task and integrate parallelly conducted tasks at the end of the architecture with one cost function. Such architecture fails to take advantage of the combined power of the features from each individual task at an early stage of the training. In this research, we propose a new architecture, FTMTLNet, an MTL enabled by feature transferring. Traditional transfer learning deals with the same or similar task from different data sources (a.k.a. domain). The underlying assumption is that the knowledge gained from source domains may help the learning task on the target domain. Our proposed FTMTLNet utilizes the different tasks from the same domain. Considering features from the tasks are different views of the domain, the combined feature maps can be well exploited using knowledge from multiple views to enhance the generalizability. To evaluate the validity of the proposed approach, FTMTLNet is compared with models from literature including 8 classification models, 4 detection models and 3 segmentation models using a public full field digital mammogram dataset for breast cancer diagnosis. Experimental results show that the proposed FTMTLNet outperforms the competing models in classification and detection and has comparable results in segmentation.

arXiv:2306.16604

A Structurally Regularized CNN Architecture via Adaptive Subband Decomposition

We propose a generalized convolutional neural network (CNN) architecture that first decomposes the input signal into subbands by an adaptive filter bank structure, and then uses convolutional layers to extract features from each subband independently. Fully connected layers finally combine the extracted features to perform classification. The proposed architecture restrains each of the subband CNNs from learning using the entire input signal spectrum, resulting in structural regularization. Our proposed CNN architecture is fully compatible with the end-to-end learning mechanism of typical CNN architectures and learns the subband decomposition from the input dataset. We show that the proposed CNN architecture has attractive properties, such as robustness to input and weight-and-bias quantization noise, compared to regular full-band CNN architectures. Importantly, the proposed architecture significantly reduces computational costs, while maintaining state-of-the-art classification accuracy. Experiments on image classification tasks using the MNIST, CIFAR-10/100, Caltech-101, and ImageNet-2012 datasets show that the proposed architecture allows accuracy surpassing state-of-the-art results. On the ImageNet-2012 dataset, we achieved top-5 and top-1 validation set accuracy of 86.91% and 69.73%, respectively. Notably, the proposed architecture offers over 90% reduction in computation cost in the inference path and approximately 75% reduction in back-propagation (per iteration) with just a single-layer subband decomposition. With a 2-layer subband decomposition, the computational gains are even more significant with comparable accuracy results to the single-layer decomposition.

arXiv:2606.18063v1cs.CV

LLM이 흉터를 분석할 때: 이미지에서 임상적으로 유의미한 특징으로

When LLMs Analyze Scars: From Images to Clinically-Meaningful Features

의료 이미지 분류는 근본적인 딜레마에 직면해 있습니다. 심층 학습 모델은 대규모로 놀라운 성능을 달성하지만, 실제 임상 시나리오에서는 라벨링 비용, 프라이버시 제약, 희귀 질환 등으로 인해 심각한 데이터 부족 문제를 겪습니다. 이러한 문제는 병리적 흉터 분류에서 특히 두드러지는데, 켈로이드와 비후성 흉터를 구별하는 데에는 정교한 전문 지식이 필요하며 라벨링된 이미지가 극도로 제한적입니다. 본 연구에서는 대규모 언어 모델(LLM)을 엔드투엔드 분류기가 아닌 지식 기반 특징 엔지니어로 재정의하는 새로운 패러다임을 제안합니다. 우리는 이 프레임워크를 ScaFE(Scar Feature Engineering)라고 명명했습니다. 핵심 통찰은 LLM이 풍부한 의료 지식을 인코딩하고 있으며, 이를 실행 가능한 특징 추출 코드로 외부화하여 고차원 이미지를 저차원의 임상적으로 해석 가능한 표현으로 변환할 수 있다는 점입니다. 구체적으로, 확립된 흉터 평가 기준을 LLM에 프롬프트로 제공하여 밴쿠버 흉터 척도(Vancouver Scar Scale)와 같은 임상 점수 체계에 부합하는 특징을 추출하는 결정론적 파이썬 코드를 생성하도록 합니다. 우리의 접근 방식은 세 가지 핵심 이점을 제공합니다: (1) 데이터 효율성, 지식 습득을 통계적 학습과 분리하여 제한된 학습 샘플로도 강건한 성능을 달성할 수 있음; (2) 프라이버시 보존, 원본 이미지가 외부 LLM에 노출되지 않고 로컬에서 처리됨; (3) 해석 가능성, 임상적 추론에 기반한 명시적인 특징을 통해 제공됨. 흉터 분류에 대한 광범위한 실험 결과, 제안하는 방법은 데이터가 제한된 상황에서 엔드투엔드 심층 학습 베이스라인이나 블랙박스 분류기로 사용된 LLM보다 일관되게 우수한 성능을 보임을 확인했습니다. 이는 데이터 효율적이고 임상적으로 투명한 의료 AI 시스템에 LLM을 통합하는 유망한 방향을 제시합니다.

arXiv:2211.15143

Explaining Deep Convolutional Neural Networks for Image Classification by Evolving Local Interpretable Model-agnostic Explanations

Deep convolutional neural networks have proven their effectiveness, and have been acknowledged as the most dominant method for image classification. However, a severe drawback of deep convolutional neural networks is poor explainability. Unfortunately, in many real-world applications, users need to understand the rationale behind the predictions of deep convolutional neural networks when determining whether they should trust the predictions or not. To resolve this issue, a novel genetic algorithm-based method is proposed for the first time to automatically evolve local explanations that can assist users to assess the rationality of the predictions. Furthermore, the proposed method is model-agnostic, i.e., it can be utilised to explain any deep convolutional neural network models. In the experiments, ResNet is used as an example model to be explained, and the ImageNet dataset is selected as the benchmark dataset. DenseNet and MobileNet are further explained to demonstrate the model-agnostic characteristic of the proposed method. The evolved local explanations on four images, randomly selected from ImageNet, are presented, which show that the evolved local explanations are straightforward to be recognised by humans. Moreover, the evolved explanations can explain the predictions of deep convolutional neural networks on all four images very well by successfully capturing meaningful interpretable features of the sample images. Further analysis based on the 30 runs of the experiments exhibits that the evolved local explanations can also improve the probabilities/confidences of the deep convolutional neural network models in making the predictions. The proposed method can obtain local explanations within one minute, which is more than ten times faster than LIME (the state-of-the-art method).

arXiv:2501.13341공식 코드 · Papers with Code

Multi-aspect Knowledge Distillation with Large Language Model

Recent advancements in deep learning have significantly improved performance on computer vision tasks. Previous image classification methods primarily modify model architectures or add features, and they optimize models using cross-entropy loss on class logits. Since they focus on classifying images with considering class labels, these methods may struggle to learn various \emph{aspects} of classes (e.g., natural positions and shape changes). Rethinking the previous approach from a novel view, we propose a multi-aspect knowledge distillation method using Multimodal Large Language Models (MLLMs). Our approach involves: 1) querying Large Language Model with multi-aspect questions relevant to the knowledge we want to transfer to the model, 2) extracting corresponding logits from MLLM, and 3) expanding the model's output dimensions to distill these multi-aspect logits. We then apply cross-entropy loss to class logits and binary cross-entropy loss to multi-aspect logits. Through our method, the model can learn not only the knowledge about visual aspects but also the abstract and complex aspects that require a deeper understanding. We primarily apply our method to image classification, and to explore the potential for extending our model, we expand it to other tasks, such as object detection. In all experimental results, our method improves the performance of the baselines. Additionally, we analyze the effect of multi-aspect knowledge distillation. These results demonstrate that our method can transfer knowledge about various aspects to the model and the aspect knowledge can enhance model performance in computer vision tasks. This paper demonstrates the great potential of multi-aspect knowledge distillation, and we believe it offers a promising direction for future research in computer vision and beyond.

arXiv:1805.00355

Sample-to-Sample Correspondence for Unsupervised Domain Adaptation

The assumption that training and testing samples are generated from the same distribution does not always hold for real-world machine-learning applications. The procedure of tackling this discrepancy between the training (source) and testing (target) domains is known as domain adaptation. We propose an unsupervised version of domain adaptation that considers the presence of only unlabelled data in the target domain. Our approach centers on finding correspondences between samples of each domain. The correspondences are obtained by treating the source and target samples as graphs and using a convex criterion to match them. The criteria used are first-order and second-order similarities between the graphs as well as a class-based regularization. We have also developed a computationally efficient routine for the convex optimization, thus allowing the proposed method to be used widely. To verify the effectiveness of the proposed method, computer simulations were conducted on synthetic, image classification and sentiment classification datasets. Results validated that the proposed local sample-to-sample matching method out-performs traditional moment-matching methods and is competitive with respect to current local domain-adaptation methods.

arXiv:1802.07623공식 코드 · Papers with Code

Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives

In this paper we propose a novel method that provides contrastive explanations justifying the classification of an input by a black box classifier such as a deep neural network. Given an input we find what should be %necessarily and minimally and sufficiently present (viz. important object pixels in an image) to justify its classification and analogously what should be minimally and necessarily \emph{absent} (viz. certain background pixels). We argue that such explanations are natural for humans and are used commonly in domains such as health care and criminology. What is minimally but critically \emph{absent} is an important part of an explanation, which to the best of our knowledge, has not been explicitly identified by current explanation methods that explain predictions of neural networks. We validate our approach on three real datasets obtained from diverse domains; namely, a handwritten digits dataset MNIST, a large procurement fraud dataset and a brain activity strength dataset. In all three cases, we witness the power of our approach in generating precise explanations that are also easy for human experts to understand and evaluate.

arXiv:1810.07122

Robust Gesture-Based Communication for Underwater Human-Robot Interaction in the context of Search and Rescue Diver Missions

We propose a robust gesture-based communication pipeline for divers to instruct an Autonomous Underwater Vehicle (AUV) to assist them in performing high-risk tasks and helping in case of emergency. A gesture communication language (CADDIAN) is developed, based on consolidated and standardized diver gestures, including an alphabet, syntax and semantics, ensuring a logical consistency. A hierarchical classification approach is introduced for hand gesture recognition based on stereo imagery and multi-descriptor aggregation to specifically cope with underwater image artifacts, e.g. light backscatter or color attenuation. Once the classification task is finished, a syntax check is performed to filter out invalid command sequences sent by the diver or generated by errors in the classifier. Throughout this process, the diver receives constant feedback from an underwater tablet to acknowledge or abort the mission at any time. The objective is to prevent the AUV from executing unnecessary, infeasible or potentially harmful motions. Experimental results under different environmental conditions in archaeological exploration and bridge inspection applications show that the system performs well in the field.