PyTorchKR Papers

“Image Classification”

총 18,385편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2310.13906

Exploring Driving Behavior for Autonomous Vehicles Based on Gramian Angular Field Vision Transformer

Effective classification of autonomous vehicle (AV) driving behavior emerges as a critical area for diagnosing AV operation faults, enhancing autonomous driving algorithms, and reducing accident rates. This paper presents the Gramian Angular Field Vision Transformer (GAF-ViT) model, designed to analyze AV driving behavior. The proposed GAF-ViT model consists of three key components: GAF Transformer Module, Channel Attention Module, and Multi-Channel ViT Module. These modules collectively convert representative sequences of multivariate behavior into multi-channel images and employ image recognition techniques for behavior classification. A channel attention mechanism is applied to multi-channel images to discern the impact of various driving behavior features. Experimental evaluation on the Waymo Open Dataset of trajectories demonstrates that the proposed model achieves state-of-the-art performance. Furthermore, an ablation study effectively substantiates the efficacy of individual modules within the model.

arXiv:2409.04761

Transformer Based Tissue Classification in Robotic Needle Biopsy

Image-guided minimally invasive robotic surgery is commonly employed for tasks such as needle biopsies or localized therapies. However, the nonlinear deformation of various tissue types presents difficulties for surgeons in achieving precise needle tip placement, particularly when relying on low-fidelity biopsy imaging systems. In this paper, we introduce a method to classify needle biopsy interventions and identify tissue types based on a comprehensive needle-tissue contact model that incorporates both position and force parameters. We trained a transformer model using a comprehensive dataset collected from a formerly developed robotics platform, which consists of synthetic and porcine tissue from various locations (liver, kidney, heart, belly, hock) marked with interaction phases (pre-puncture, puncture, post-puncture, neutral). This model achieves a significant classification accuracy of 0.93. Our demonstrated method can assist surgeons in identifying transitions to different tissues, aiding surgeons with tissue awareness.

arXiv:2501.18793

OT-Transformer: A Continuous-time Transformer Architecture with Optimal Transport Regularization

Transformers have achieved state-of-the-art performance in numerous tasks. In this paper, we propose a continuous-time formulation of transformers. Specifically, we consider a dynamical system whose governing equation is parametrized by transformer blocks. We leverage optimal transport theory to regularize the training problem, which enhances stability in training and improves generalization of the resulting model. Moreover, we demonstrate in theory that this regularization is necessary as it promotes uniqueness and regularity of solutions. Our model is flexible in that almost any existing transformer architectures can be adopted to construct the dynamical system with only slight modifications to the existing code. We perform extensive numerical experiments on tasks motivated by natural language processing, image classification, and point cloud classification. Our experimental results show that the proposed method improves the performance of its discrete counterpart and outperforms relevant comparing models.

arXiv:2505.07256

Synthetic Similarity Search in Automotive Production

Visual quality inspection in automotive production is essential for ensuring the safety and reliability of vehicles. Computer vision (CV) has become a popular solution for these inspections due to its cost-effectiveness and reliability. However, CV models require large, annotated datasets, which are costly and time-consuming to collect. To reduce the need for extensive training data, we propose a novel image classification pipeline that combines similarity search using a vision-based foundation model with synthetic data. Our approach leverages a DINOv2 model to transform input images into feature vectors, which are then compared to pre-classified reference images using cosine distance measurements. By utilizing synthetic data instead of real images as references, our pipeline achieves high classification accuracy without relying on real data. We evaluate this approach in eight real-world inspection scenarios and demonstrate that it meets the high performance requirements of production environments.

arXiv:2606.16794v2cs.CV

얼굴 피부 질환 분류 모델의 설명 가능성 평가를 위한 LLM 기반 시각적 설명 평가 프레임워크

LLM-Based Visual Explanation Evaluation Framework for Assessing the Explainability of Facial Skin Disease Classification Models

본 연구는 얼굴 피부 질환 진단에서 시각적 어텐션 설명을 평가하기 위한 도메인 특화 LLM 기반 시각적 설명 평가 프레임워크를 제안한다. 기존 연구는 주로 분류 성능 향상에 초점을 맞춰 왔으나, 시각적 설명이 임상적으로 관련 있는 병변 영역에 그라운딩(grounding)되어 있는지를 체계적으로 검토한 연구는 상대적으로 적다. 본 연구에서는 얼굴 피부 질환 이미지로부터 병변 중심의 어텐션 맵을 생성하기 위해 이미지 기반 시각적 어텐션 생성 알고리즘을 개발했다. 기존의 그래디언트 기반 설명 가능성 방법과 달리, 제안된 접근법은 색상 현저성(color saliency), 얼굴 공간 사전(facial spatial priors), 가우시안 스무딩(Gaussian smoothing), 어텐션 오버레이 시각화를 결합하여 임상적으로 해석 가능한 어텐션 맵을 생성한다. 또한 GPT-5.5, Gemini 3.5 Flash, Claude Sonnet 4.6을 사용하여 LLM-as-a-judge 평가 프레임워크를 설계하고, 병변 국소화와 설명 신뢰성 관점에서 생성된 시각적 설명을 평가했다.

arXiv:2010.15487

Beyond cross-entropy: learning highly separable feature distributions for robust and accurate classification

Deep learning has shown outstanding performance in several applications including image classification. However, deep classifiers are known to be highly vulnerable to adversarial attacks, in that a minor perturbation of the input can easily lead to an error. Providing robustness to adversarial attacks is a very challenging task especially in problems involving a large number of classes, as it typically comes at the expense of an accuracy decrease. In this work, we propose the Gaussian class-conditional simplex (GCCS) loss: a novel approach for training deep robust multiclass classifiers that provides adversarial robustness while at the same time achieving or even surpassing the classification accuracy of state-of-the-art methods. Differently from other frameworks, the proposed method learns a mapping of the input classes onto target distributions in a latent space such that the classes are linearly separable. Instead of maximizing the likelihood of target labels for individual samples, our objective function pushes the network to produce feature distributions yielding high inter-class separation. The mean values of the distributions are centered on the vertices of a simplex such that each class is at the same distance from every other class. We show that the regularization of the latent space based on our approach yields excellent classification accuracy and inherently provides robustness to multiple adversarial attacks, both targeted and untargeted, outperforming state-of-the-art approaches over challenging datasets.

arXiv:2106.04716

Labeled Data Generation with Inexact Supervision

The recent advanced deep learning techniques have shown the promising results in various domains such as computer vision and natural language processing. The success of deep neural networks in supervised learning heavily relies on a large amount of labeled data. However, obtaining labeled data with target labels is often challenging due to various reasons such as cost of labeling and privacy issues, which challenges existing deep models. In spite of that, it is relatively easy to obtain data with \textit{inexact supervision}, i.e., having labels/tags related to the target task. For example, social media platforms are overwhelmed with billions of posts and images with self-customized tags, which are not the exact labels for target classification tasks but are usually related to the target labels. It is promising to leverage these tags (inexact supervision) and their relations with target classes to generate labeled data to facilitate the downstream classification tasks. However, the work on this is rather limited. Therefore, we study a novel problem of labeled data generation with inexact supervision. We propose a novel generative framework named as ADDES which can synthesize high-quality labeled data for target classification tasks by learning from data with inexact supervision and the relations between inexact supervision and target classes. Experimental results on image and text datasets demonstrate the effectiveness of the proposed ADDES for generating realistic labeled data from inexact supervision to facilitate the target classification task.

arXiv:2210.07183공식 코드 · Papers with Code

Visual Classification via Description from Large Language Models

Vision-language models (VLMs) such as CLIP have shown promising performance on a variety of recognition tasks using the standard zero-shot classification procedure -- computing similarity between the query image and the embedded words for each category. By only using the category name, they neglect to make use of the rich context of additional information that language affords. The procedure gives no intermediate understanding of why a category is chosen, and furthermore provides no mechanism for adjusting the criteria used towards this decision. We present an alternative framework for classification with VLMs, which we call classification by description. We ask VLMs to check for descriptive features rather than broad categories: to find a tiger, look for its stripes; its claws; and more. By basing decisions on these descriptors, we can provide additional cues that encourage using the features we want to be used. In the process, we can get a clear idea of what features the model uses to construct its decision; it gains some level of inherent explainability. We query large language models (e.g., GPT-3) for these descriptors to obtain them in a scalable way. Extensive experiments show our framework has numerous advantages past interpretability. We show improvements in accuracy on ImageNet across distribution shifts; demonstrate the ability to adapt VLMs to recognize concepts unseen during training; and illustrate how descriptors can be edited to effectively mitigate bias compared to the baseline.

arXiv:2210.16380

Incorporating Crowdsourced Annotator Distributions into Ensemble Modeling to Improve Classification Trustworthiness for Ancient Greek Papyri

Performing classification on noisy, crowdsourced image datasets can prove challenging even for the best neural networks. Two issues which complicate the problem on such datasets are class imbalance and ground-truth uncertainty in labeling. The AL-ALL and AL-PUB datasets - consisting of tightly cropped, individual characters from images of ancient Greek papyri - are strongly affected by both issues. The application of ensemble modeling to such datasets can help identify images where the ground-truth is questionable and quantify the trustworthiness of those samples. As such, we apply stacked generalization consisting of nearly identical ResNets with different loss functions: one utilizing sparse cross-entropy (CXE) and the other Kullback-Liebler Divergence (KLD). Both networks use labels drawn from a crowd-sourced consensus. This consensus is derived from a Normalized Distribution of Annotations (NDA) based on all annotations for a given character in the dataset. For the second network, the KLD is calculated with respect to the NDA. For our ensemble model, we apply a k-nearest neighbors model to the outputs of the CXE and KLD networks. Individually, the ResNet models have approximately 93% accuracy, while the ensemble model achieves an accuracy of > 95%, increasing the classification trustworthiness. We also perform an analysis of the Shannon entropy of the various models' output distributions to measure classification uncertainty. Our results suggest that entropy is useful for predicting model misclassifications.

arXiv:2608.25965v1cs.CV

윤곽선은 줄이고 정확도는 높이다: 난소 초음파 분류를 위한 병변 유도 ROI 심층 학습

Less Contouring, More Accuracy: Lesion-Guided ROI Deep Learning for Ovarian Ultrasound Classification

경질 초음파(transvaginal ultrasound)를 이용한 난소 병변 분류는 영상 특성이 서로 겹치고 전문가의 판독에 의존해야 하기 때문에 여전히 어려운 과제로 남아 있다. 본 연구는 병변 유도 관심 영역(region-of-interest, ROI) 심층 학습이 픽셀 단위 병변 분할(segmentation)에 따르는 어노테이션 부담을 줄이면서도 경쟁력 있는 진단 성능을 달성할 수 있는지 조사한다. 공개된 두 가지 난소 초음파 데이터셋을 평가하였으며, 8개 클래스 분류에는 Multi-Modality Ovarian Tumor Ultrasound(MMOTU) 데이터셋을, 이진 분류에는 Ovarian Ultrasound Dataset(OUD)을 사용하였다. 통합된 프레임워크 하에서 네 가지 전략을 비교하였다: 전역 이미지 기반 심층 학습, 병변 유도 ROI 기반 심층 학습, 병변 윤곽선(contour) 기반 심층 학습, 그리고 머신러닝 분류기를 결합한 윤곽선 기반 라디오믹스(radiomics)이다. 네 가지 심층 학습 아키텍처인 MaxViT-Tiny, Swin Transformer, EfficientNet-B7, ResNet18을 평가하였다. 라디오믹스 모델은 서포트 벡터 머신(support vector machine), k-최근접 이웃(k-nearest neighbors), 인공 신경망(artificial neural network) 분류기를 사용하여 개발하였고, 표본 수가 더 적은 OUD 데이터셋에는 ANOVA 기반 특징 선택을 적용하였다. 병변 유도 ROI 전략이 전반적으로 가장 우수한 성능을 보였으며, MaxViT-Tiny는 MMOTU에서 정확도 93.10%와 AUC 0.99를, OUD에서 정확도 97.56%와 AUC 0.99를 기록하였다. 윤곽선 기반 접근법은 이에 견줄 만한 정확도를 달성했지만 훨씬 더 많은 어노테이션 노력이 필요하였다. 이러한 결과는 병변 유도 ROI 심층 학습이 진단 성능과 어노테이션 효율 사이에서 효과적인 균형을 제공하며, 확장 가능한 AI 지원 난소 초음파 분석을 위한 실용적인 접근법이 될 수 있음을 보여준다.

arXiv:1812.00329

Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning

Learning visual features from unlabeled image data is an important yet challenging task, which is often achieved by training a model on some annotation-free information. We consider spatial contexts, for which we solve so-called jigsaw puzzles, i.e., each image is cut into grids and then disordered, and the goal is to recover the correct configuration. Existing approaches formulated it as a classification task by defining a fixed mapping from a small subset of configurations to a class set, but these approaches ignore the underlying relationship between different configurations and also limit their application to more complex scenarios. This paper presents a novel approach which applies to jigsaw puzzles with an arbitrary grid size and dimensionality. We provide a fundamental and generalized principle, that weaker cues are easier to be learned in an unsupervised manner and also transfer better. In the context of puzzle recognition, we use an iterative manner which, instead of solving the puzzle all at once, adjusts the order of the patches in each step until convergence. In each step, we combine both unary and binary features on each patch into a cost function judging the correctness of the current configuration. Our approach, by taking similarity between puzzles into consideration, enjoys a more reasonable way of learning visual knowledge. We verify the effectiveness of our approach in two aspects. First, it is able to solve arbitrarily complex puzzles, including high-dimensional puzzles, that prior methods are difficult to handle. Second, it serves as a reliable way of network initialization, which leads to better transfer performance in a few visual recognition tasks including image classification, object detection, and semantic segmentation.

arXiv:2303.15823공식 코드 · Papers with Code

Automated wildlife image classification: An active learning tool for ecological applications

Wildlife camera trap images are being used extensively to investigate animal abundance, habitat associations, and behavior, which is complicated by the fact that experts must first classify the images manually. Artificial intelligence systems can take over this task but usually need a large number of already-labeled training images to achieve sufficient performance. This requirement necessitates human expert labor and poses a particular challenge for projects with few cameras or short durations. We propose a label-efficient learning strategy that enables researchers with small or medium-sized image databases to leverage the potential of modern machine learning, thus freeing crucial resources for subsequent analyses. Our methodological proposal is two-fold: (1) We improve current strategies of combining object detection and image classification by tuning the hyperparameters of both models. (2) We provide an active learning (AL) system that allows training deep learning models very efficiently in terms of required human-labeled training images. We supply a software package that enables researchers to use these methods directly and thereby ensure the broad applicability of the proposed framework in ecological practice. We show that our tuning strategy improves predictive performance. We demonstrate how the AL pipeline reduces the amount of pre-labeled data needed to achieve a specific predictive performance and that it is especially valuable for improving out-of-sample predictive performance. We conclude that the combination of tuning and AL increases predictive performance substantially. Furthermore, we argue that our work can broadly impact the community through the ready-to-use software package provided. Finally, the publication of our models tailored to European wildlife data enriches existing model bases mostly trained on data from Africa and North America.

arXiv:2402.03783

Exploring Low-Resource Medical Image Classification with Weakly Supervised Prompt Learning

Most advances in medical image recognition supporting clinical auxiliary diagnosis meet challenges due to the low-resource situation in the medical field, where annotations are highly expensive and professional. This low-resource problem can be alleviated by leveraging the transferable representations of large-scale pre-trained vision-language models via relevant medical text prompts. However, existing pre-trained vision-language models require domain experts to carefully design the medical prompts, which greatly increases the burden on clinicians. To address this problem, we propose a weakly supervised prompt learning method MedPrompt to automatically generate medical prompts, which includes an unsupervised pre-trained vision-language model and a weakly supervised prompt learning model. The unsupervised pre-trained vision-language model utilizes the natural correlation between medical images and corresponding medical texts for pre-training, without any manual annotations. The weakly supervised prompt learning model only utilizes the classes of images in the dataset to guide the learning of the specific class vector in the prompt, while the learning of other context vectors in the prompt requires no manual annotations for guidance. To the best of our knowledge, this is the first model to automatically generate medical prompts. With these prompts, the pre-trained vision-language model can be freed from the strong expert dependency of manual annotation and manual prompt design. Experimental results show that the model using our automatically generated prompts outperforms its full-shot learning hand-crafted prompts counterparts with only a minimal number of labeled samples for few-shot learning, and reaches superior or comparable accuracy on zero-shot image classification. The proposed prompt generator is lightweight and therefore can be embedded into any network architecture.

arXiv:1602.03930

Global Deconvolutional Networks for Semantic Segmentation

Semantic image segmentation is a principal problem in computer vision, where the aim is to correctly classify each individual pixel of an image into a semantic label. Its widespread use in many areas, including medical imaging and autonomous driving, has fostered extensive research in recent years. Empirical improvements in tackling this task have primarily been motivated by successful exploitation of Convolutional Neural Networks (CNNs) pre-trained for image classification and object recognition. However, the pixel-wise labelling with CNNs has its own unique challenges: (1) an accurate deconvolution, or upsampling, of low-resolution output into a higher-resolution segmentation mask and (2) an inclusion of global information, or context, within locally extracted features. To address these issues, we propose a novel architecture to conduct the equivalent of the deconvolution operation globally and acquire dense predictions. We demonstrate that it leads to improved performance of state-of-the-art semantic segmentation models on the PASCAL VOC 2012 benchmark, reaching 74.0% mean IU accuracy on the test set.

arXiv:1908.06066

Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training

We propose Unicoder-VL, a universal encoder that aims to learn joint representations of vision and language in a pre-training manner. Borrow ideas from cross-lingual pre-trained models, such as XLM and Unicoder, both visual and linguistic contents are fed into a multi-layer Transformer for the cross-modal pre-training, where three pre-trained tasks are employed, including Masked Language Modeling (MLM), Masked Object Classification (MOC) and Visual-linguistic Matching (VLM). The first two tasks learn context-aware representations for input tokens based on linguistic and visual contents jointly. The last task tries to predict whether an image and a text describe each other. After pretraining on large-scale image-caption pairs, we transfer Unicoder-VL to caption-based image-text retrieval and visual commonsense reasoning, with just one additional output layer. We achieve state-of-the-art or comparable results on both two tasks and show the powerful ability of the cross-modal pre-training.

arXiv:1911.01769공식 코드 · Papers with Code

Visual Privacy Protection via Mapping Distortion

Privacy protection is an important research area, which is especially critical in this big data era. To a large extent, the privacy of visual classification data is mainly in the mapping between the image and its corresponding label, since this relation provides a great amount of information and can be used in other scenarios. In this paper, we propose the mapping distortion based protection (MDP) and its augmentation-based extension (AugMDP) to protect the data privacy by modifying the original dataset. In the modified dataset generated by MDP, the image and its label are not consistent ($e.g.$, a cat-like image is labeled as the dog), whereas the DNNs trained on it can still achieve good performance on benign testing set. As such, this method can protect privacy when the dataset is leaked. Extensive experiments are conducted, which verify the effectiveness and feasibility of our method. The code for reproducing main results is available at \url{https://github.com/PerdonLiu/Visual-Privacy-Protection-via-Mapping-Distortion}.

arXiv:2001.06538

Adapting Grad-CAM for Embedding Networks

The gradient-weighted class activation mapping (Grad-CAM) method can faithfully highlight important regions in images for deep model prediction in image classification, image captioning and many other tasks. It uses the gradients in back-propagation as weights (grad-weights) to explain network decisions. However, applying Grad-CAM to embedding networks raises significant challenges because embedding networks are trained by millions of dynamically paired examples (e.g. triplets). To overcome these challenges, we propose an adaptation of the Grad-CAM method for embedding networks. First, we aggregate grad-weights from multiple training examples to improve the stability of Grad-CAM. Then, we develop an efficient weight-transfer method to explain decisions for any image without back-propagation. We extensively validate the method on the standard CUB200 dataset in which our method produces more accurate visual attention than the original Grad-CAM method. We also apply the method to a house price estimation application using images. The method produces convincing qualitative results, showcasing the practicality of our approach.

arXiv:2208.07828

Learning Facial Liveness Representation for Domain Generalized Face Anti-spoofing

Face anti-spoofing (FAS) aims at distinguishing face spoof attacks from the authentic ones, which is typically approached by learning proper models for performing the associated classification task. In practice, one would expect such models to be generalized to FAS in different image domains. Moreover, it is not practical to assume that the type of spoof attacks would be known in advance. In this paper, we propose a deep learning model for addressing the aforementioned domain-generalized face anti-spoofing task. In particular, our proposed network is able to disentangle facial liveness representation from the irrelevant ones (i.e., facial content and image domain features). The resulting liveness representation exhibits sufficient domain invariant properties, and thus it can be applied for performing domain-generalized FAS. In our experiments, we conduct experiments on five benchmark datasets with various settings, and we verify that our model performs favorably against state-of-the-art approaches in identifying novel types of spoof attacks in unseen image domains.

arXiv:2302.08722

GPT4MIA: Utilizing Generative Pre-trained Transformer (GPT-3) as A Plug-and-Play Transductive Model for Medical Image Analysis

In this paper, we propose a novel approach (called GPT4MIA) that utilizes Generative Pre-trained Transformer (GPT) as a plug-and-play transductive inference tool for medical image analysis (MIA). We provide theoretical analysis on why a large pre-trained language model such as GPT-3 can be used as a plug-and-play transductive inference model for MIA. At the methodological level, we develop several technical treatments to improve the efficiency and effectiveness of GPT4MIA, including better prompt structure design, sample selection, and prompt ordering of representative samples/features. We present two concrete use cases (with workflow) of GPT4MIA: (1) detecting prediction errors and (2) improving prediction accuracy, working in conjecture with well-established vision-based models for image classification (e.g., ResNet). Experiments validate that our proposed method is effective for these two tasks. We further discuss the opportunities and challenges in utilizing Transformer-based large language models for broader MIA applications.

arXiv:2305.06912공식 코드 · Papers with Code

Meta-Learners for Few-Shot Weakly-Supervised Medical Image Segmentation

Most uses of Meta-Learning in visual recognition are very often applied to image classification, with a relative lack of works in other tasks {such} as segmentation and detection. We propose a generic Meta-Learning framework for few-shot weakly-supervised segmentation in medical imaging domains. We conduct a comparative analysis of meta-learners from distinct paradigms adapted to few-shot image segmentation in different sparsely annotated radiological tasks. The imaging modalities include 2D chest, mammographic and dental X-rays, as well as 2D slices of volumetric tomography and resonance images. Our experiments consider a total of 9 meta-learners, 4 backbones and multiple target organ segmentation tasks. We explore small-data scenarios in radiology with varying weak annotation styles and densities. Our analysis shows that metric-based meta-learning approaches achieve better segmentation results in tasks with smaller domain shifts in comparison to the meta-training datasets, while some gradient- and fusion-based meta-learners are more generalizable to larger domain shifts.