PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2405.19186

MetaToken: Detecting Hallucination in Image Descriptions by Meta Classification

Large Vision Language Models (LVLMs) have shown remarkable capabilities in multimodal tasks like visual question answering or image captioning. However, inconsistencies between the visual information and the generated text, a phenomenon referred to as hallucinations, remain an unsolved problem with regard to the trustworthiness of LVLMs. To address this problem, recent works proposed to incorporate computationally costly Large (Vision) Language Models in order to detect hallucinations on a sentence- or subsentence-level. In this work, we introduce MetaToken, a lightweight binary classifier to detect hallucinations on the token-level at negligible cost. Based on a statistical analysis, we reveal key factors of hallucinations in LVLMs. MetaToken can be applied to any open-source LVLM without any knowledge about ground truth data providing a calibrated detection of hallucinations. We evaluate our method on four state-of-the-art LVLMs demonstrating the effectiveness of our approach.

arXiv:2504.08710

Hypergraph Vision Transformers: Images are More than Nodes, More than Edges

Recent advancements in computer vision have highlighted the scalability of Vision Transformers (ViTs) across various tasks, yet challenges remain in balancing adaptability, computational efficiency, and the ability to model higher-order relationships. Vision Graph Neural Networks (ViGs) offer an alternative by leveraging graph-based methodologies but are hindered by the computational bottlenecks of clustering algorithms used for edge generation. To address these issues, we propose the Hypergraph Vision Transformer (HgVT), which incorporates a hierarchical bipartite hypergraph structure into the vision transformer framework to capture higher-order semantic relationships while maintaining computational efficiency. HgVT leverages population and diversity regularization for dynamic hypergraph construction without clustering, and expert edge pooling to enhance semantic extraction and facilitate graph-based image retrieval. Empirical results demonstrate that HgVT achieves strong performance on image classification and retrieval, positioning it as an efficient framework for semantic-based vision tasks.

arXiv:2112.09532공식 코드 · Papers with Code

Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition

Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size. Therefore, we propose Pixel Distillation that extends knowledge distillation into the input level while simultaneously breaking architecture constraints. Such a scheme can achieve flexible cost control for deployment, as it allows the system to adjust both network architecture and image quality according to the overall requirement of resources. Specifically, we first propose an input spatial representation distillation (ISRD) mechanism to transfer spatial knowledge from large images to student's input module, which can facilitate stable knowledge transfer between CNN and ViT. Then, a Teacher-Assistant-Student (TAS) framework is further established to disentangle pixel distillation into the model compression stage and input compression stage, which significantly reduces the overall complexity of pixel distillation and the difficulty of distilling intermediate knowledge. Finally, we adapt pixel distillation to object detection via an aligned feature for preservation (AFP) strategy for TAS, which aligns output dimensions of detectors at each stage by manipulating features and anchors of the assistant. Comprehensive experiments on image classification and object detection demonstrate the effectiveness of our method. Code is available at https://github.com/gyguo/PixelDistillation.

arXiv:2307.13125

Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review

Deep learning has become a popular tool for medical image analysis, but the limited availability of training data remains a major challenge, particularly in the medical field where data acquisition can be costly and subject to privacy regulations. Data augmentation techniques offer a solution by artificially increasing the number of training samples, but these techniques often produce limited and unconvincing results. To address this issue, a growing number of studies have proposed the use of deep generative models to generate more realistic and diverse data that conform to the true distribution of the data. In this review, we focus on three types of deep generative models for medical image augmentation: variational autoencoders, generative adversarial networks, and diffusion models. We provide an overview of the current state of the art in each of these models and discuss their potential for use in different downstream tasks in medical imaging, including classification, segmentation, and cross-modal translation. We also evaluate the strengths and limitations of each model and suggest directions for future research in this field. Our goal is to provide a comprehensive review about the use of deep generative models for medical image augmentation and to highlight the potential of these models for improving the performance of deep learning algorithms in medical image analysis.

arXiv:2402.16315

Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models

Recent advances in instruction-tuned Large Vision-Language Models (LVLMs) have imbued the models with the ability to generate high-level, image-grounded explanations with ease. While such capability is largely attributed to the rich world knowledge contained within the Large Language Models (LLMs), our work reveals their shortcomings in fine-grained visual categorization (FGVC) across six different benchmark settings. Most recent state-of-the-art LVLMs like LLaVa-1.5, InstructBLIP and GPT-4V not only severely deteriorate in terms of classification performance, e.g., average drop of 65.58 in EM for Stanford Dogs for LLaVA-1.5, but also struggle to generate an accurate explanation with detailed attributes based on the concept that appears within an input image despite their capability to generate holistic image-level descriptions. In-depth analyses show that instruction-tuned LVLMs exhibit modality gap, showing discrepancy when given textual and visual inputs that correspond to the same concept, preventing the image modality from leveraging the rich parametric knowledge within the LLMs. In an effort to further the community's endeavor in this direction, we propose a multiple granularity attribute-centric evaluation benchmark, Finer, which aims to establish a ground to evaluate LVLMs' fine-grained visual comprehension ability and provide significantly improved explainability.

arXiv:2503.08455공식 코드 · Papers with Code

Controlling Latent Diffusion Using Latent CLIP

Instead of performing text-conditioned denoising in the image domain, latent diffusion models (LDMs) operate in latent space of a variational autoencoder (VAE), enabling more efficient processing at reduced computational costs. However, while the diffusion process has moved to the latent space, the contrastive language-image pre-training (CLIP) models, as used in many image processing tasks, still operate in pixel space. Doing so requires costly VAE-decoding of latent images before they can be processed. In this paper, we introduce Latent-CLIP, a CLIP model that operates directly in the latent space. We train Latent-CLIP on 2.7B pairs of latent images and descriptive texts, and show that it matches zero-shot classification performance of similarly sized CLIP models on both the ImageNet benchmark and a LDM-generated version of it, demonstrating its effectiveness in assessing both real and generated content. Furthermore, we construct Latent-CLIP rewards for reward-based noise optimization (ReNO) and show that they match the performance of their CLIP counterparts on GenEval and T2I-CompBench while cutting the cost of the total pipeline by 21%. Finally, we use Latent-CLIP to guide generation away from harmful content, achieving strong performance on the inappropriate image prompts (I2P) benchmark and a custom evaluation, without ever requiring the costly step of decoding intermediate images.

arXiv:1412.0003

3D-Assisted Image Feature Synthesis for Novel Views of an Object

Comparing two images in a view-invariant way has been a challenging problem in computer vision for a long time, as visual features are not stable under large view point changes. In this paper, given a single input image of an object, we synthesize new features for other views of the same object. To accomplish this, we introduce an aligned set of 3D models in the same class as the input object image. Each 3D model is represented by a set of views, and we study the correlation of image patches between different views, seeking what we call surrogates --- patches in one view whose feature content predicts well the features of a patch in another view. In particular, for each patch in the novel desired view, we seek surrogates from the observed view of the given image. For a given surrogate, we predict that surrogate using linear combination of the corresponding patches of the 3D model views, learn the coefficients, and then transfer these coefficients on a per patch basis to synthesize the features of the patch in the novel view. In this way we can create feature sets for all views of the latent object, providing us a multi-view representation of the object. View-invariant object comparisons are achieved simply by computing the $L^2$ distances between the features of corresponding views. We provide theoretical and empirical analysis of the feature synthesis process, and evaluate the proposed view-agnostic distance (VAD) in fine-grained image retrieval (100 object classes) and classification tasks. Experimental results show that our synthesized features do enable view-independent comparison between images and perform significantly better than traditional image features in this respect.

arXiv:1812.01214

Prototype-based Neural Network Layers: Incorporating Vector Quantization

Neural networks currently dominate the machine learning community and they do so for good reasons. Their accuracy on complex tasks such as image classification is unrivaled at the moment and with recent improvements they are reasonably easy to train. Nevertheless, neural networks are lacking robustness and interpretability. Prototype-based vector quantization methods on the other hand are known for being robust and interpretable. For this reason, we propose techniques and strategies to merge both approaches. This contribution will particularly highlight the similarities between them and outline how to construct a prototype-based classification layer for multilayer networks. Additionally, we provide an alternative, prototype-based, approach to the classical convolution operation. Numerical results are not part of this report, instead the focus lays on establishing a strong theoretical framework. By publishing our framework and the respective theoretical considerations and justifications before finalizing our numerical experiments we hope to jump-start the incorporation of prototype-based learning in neural networks and vice versa.

arXiv:1906.04950

Pay Attention to Convolution Filters: Towards Fast and Accurate Fine-Grained Transfer Learning

We propose an efficient transfer learning method for adapting ImageNet pre-trained Convolutional Neural Network (CNN) to fine-grained image classification task. Conventional transfer learning methods typically face the trade-off between training time and accuracy. By adding "attention module" to each convolutional filters of the pre-trained network, we are able to rank and adjust the importance of each convolutional signal in an end-to-end pipeline. In this report, we show our method can adapt a pre-trianed ResNet50 for a fine-grained transfer learning task within few epochs and achieve accuracy above conventional transfer learning methods and close to models trained from scratch. Our model also offer interpretable result because the rank of the convolutional signal shows which convolution channels are utilized and amplified to achieve better classification result, as well as which signal should be treated as noise for the specific transfer learning task, which could be pruned to lower model size.

arXiv:1907.03164공식 코드 · Papers with Code

Towards Debugging Deep Neural Networks by Generating Speech Utterances

Deep neural networks (DNN) are able to successfully process and classify speech utterances. However, understanding the reason behind a classification by DNN is difficult. One such debugging method used with image classification DNNs is activation maximization, which generates example-images that are classified as one of the classes. In this work, we evaluate applicability of this method to speech utterance classifiers as the means to understanding what DNN "listens to". We trained a classifier using the speech command corpus and then use activation maximization to pull samples from the trained model. Then we synthesize audio from features using WaveNet vocoder for subjective analysis. We measure the quality of generated samples by objective measurements and crowd-sourced human evaluations. Results show that when combined with the prior of natural speech, activation maximization can be used to generate examples of different classes. Based on these results, activation maximization can be used to start opening up the DNN black-box in speech tasks.

arXiv:2003.12022공식 코드 · Papers with Code

Milking CowMask for Semi-Supervised Image Classification

Consistency regularization is a technique for semi-supervised learning that underlies a number of strong results for classification with few labeled data. It works by encouraging a learned model to be robust to perturbations on unlabeled data. Here, we present a novel mask-based augmentation method called CowMask. Using it to provide perturbations for semi-supervised consistency regularization, we achieve a state-of-the-art result on ImageNet with 10% labeled data, with a top-5 error of 8.76% and top-1 error of 26.06%. Moreover, we do so with a method that is much simpler than many alternatives. We further investigate the behavior of CowMask for semi-supervised learning by running many smaller scale experiments on the SVHN, CIFAR-10 and CIFAR-100 data sets, where we achieve results competitive with the state of the art, indicating that CowMask is widely applicable. We open source our code at https://github.com/google-research/google-research/tree/master/milking_cowmask

arXiv:2006.08656공식 코드 · Papers with Code

Multiscale Deep Equilibrium Models

We propose a new class of implicit networks, the multiscale deep equilibrium model (MDEQ), suited to large-scale and highly hierarchical pattern recognition domains. An MDEQ directly solves for and backpropagates through the equilibrium points of multiple feature resolutions simultaneously, using implicit differentiation to avoid storing intermediate states (and thus requiring only $O(1)$ memory consumption). These simultaneously-learned multi-resolution features allow us to train a single model on a diverse set of tasks and loss functions, such as using a single MDEQ to perform both image classification and semantic segmentation. We illustrate the effectiveness of this approach on two large-scale vision tasks: ImageNet classification and semantic segmentation on high-resolution images from the Cityscapes dataset. In both settings, MDEQs are able to match or exceed the performance of recent competitive computer vision models: the first time such performance and scale have been achieved by an implicit deep learning approach. The code and pre-trained models are at https://github.com/locuslab/mdeq .

arXiv:2006.12884

SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection

Based on the framework of multiple instance learning (MIL), tremendous works have promoted the advances of weakly supervised object detection (WSOD). However, most MIL-based methods tend to localize instances to their discriminative parts instead of the whole content. In this paper, we propose a spatial likelihood voting (SLV) module to converge the proposal localizing process without any bounding box annotations. Specifically, all region proposals in a given image play the role of voters every iteration during training, voting for the likelihood of each category in spatial dimensions. After dilating alignment on the area with large likelihood values, the voting results are regularized as bounding boxes, being used for the final classification and localization. Based on SLV, we further propose an end-to-end training framework for multi-task learning. The classification and localization tasks promote each other, which further improves the detection performance. Extensive experiments on the PASCAL VOC 2007 and 2012 datasets demonstrate the superior performance of SLV.

arXiv:2006.15528

DeepACC:Automate Chromosome Classification based on Metaphase Images using Deep Learning Framework Fused with Prior Knowledge

Chromosome classification is an important but difficult and tedious task in karyotyping. Previous methods only classify manually segmented single chromosome, which is far from clinical practice. In this work, we propose a detection based method, DeepACC, to locate and fine classify chromosomes simultaneously based on the whole metaphase image. We firstly introduce the Additive Angular Margin Loss to enhance the discriminative power of model. To alleviate batch effects, we transform decision boundary of each class case-by-case through a siamese network which make full use of prior knowledges that chromosomes usually appear in pairs. Furthermore, we take the clinically seven group criterion as a prior knowledge and design an additional Group Inner-Adjacency Loss to further reduce inter-class similarities. 3390 metaphase images from clinical laboratory are collected and labelled to evaluate the performance. Results show that the new design brings encouraging performance gains comparing to the state-of-the-art baselines.

arXiv:2009.14194

Deep Evolution for Facial Emotion Recognition

Deep facial expression recognition faces two challenges that both stem from the large number of trainable parameters: long training times and a lack of interpretability. We propose a novel method based on evolutionary algorithms, that deals with both challenges by massively reducing the number of trainable parameters, whilst simultaneously retaining classification performance, and in some cases achieving superior performance. We are robustly able to reduce the number of parameters on average by 95% (e.g. from 2M to 100k parameters) with no loss in classification accuracy. The algorithm learns to choose small patches from the image, relative to the nose, which carry the most important information about emotion, and which coincide with typical human choices of important features. Our work implements a novel form attention and shows that evolutionary algorithms are a valuable addition to machine learning in the deep learning era, both for reducing the number of parameters for facial expression recognition and for providing interpretable features that can help reduce bias.

arXiv:1907.12314

Automated interpretation of prenatal ultrasound using a predefined acquisition protocol in resource-limited countries

In this study, we combine a standardized acquisition protocol with image analysis algorithms to investigate if it is possible to automatically detect maternal risk factors without a trained sonographer. The standardized acquisition protocol can be taught to any health care worker within two hours. This protocol was acquired from 280 pregnant women at St.\ Luke's Catholic Hospital, Wolisso, Ethiopia. A VGG-like network was used to perform a frame classification for each frame within the acquired ultrasound data. This frame classification was used to automatically determine the number of fetuses and the fetal presentation. A U-net was trained to measure the fetal head circumference in all frames in which the VGG-like network detected a fetal head. This head circumference was used to estimate the gestational age. The results show that it possible automatically determine gestational age and determine fetal presentation and the potential to detect twin pregnancies using the standardized acquisition protocol.

arXiv:2207.12303

Continual Few-Shot Learning with Adversarial Class Storage

Humans have a remarkable ability to quickly and effectively learn new concepts in a continuous manner without forgetting old knowledge. Though deep learning has made tremendous successes on various computer vision tasks, it faces challenges for achieving such human-level intelligence. In this paper, we define a new problem called continual few-shot learning, in which tasks arrive sequentially and each task is associated with a few training samples. We propose Continual Meta-Learner (CML) to solve this problem. CML integrates metric-based classification and a memory-based mechanism along with adversarial learning into a meta-learning framework, which leads to the desirable properties: 1) it can quickly and effectively learn to handle a new task; 2) it overcomes catastrophic forgetting; 3) it is model-agnostic. We conduct extensive experiments on two image datasets, MiniImageNet and CIFAR100. Experimental results show that CML delivers state-of-the-art performance in terms of classification accuracy on few-shot learning tasks without catastrophic forgetting.

arXiv:2209.07578공식 코드 · Papers with Code

Pixel-wise classification in graphene-detection with tree-based machine learning algorithms

Mechanical exfoliation of graphene and its identification by optical inspection is one of the milestones in condensed matter physics that sparked the field of 2D materials. Finding regions of interest from the entire sample space and identification of layer number is a routine task potentially amenable to automatization. We propose supervised pixel-wise classification methods showing a high performance even with a small number of training image datasets that require short computational time without GPU. We introduce four different tree-based machine learning algorithms -- decision tree, random forest, extreme gradient boost, and light gradient boosting machine. We train them with five optical microscopy images of graphene, and evaluate their performances with multiple metrics and indices. We also discuss combinatorial machine learning models between the three single classifiers and assess their performances in identification and reliability. The code developed in this paper is open to the public and will be released at github.com/gjung-group/Graphene_segmentation.

arXiv:2209.12898

Optical Neural Ordinary Differential Equations

Increasing the layer number of on-chip photonic neural networks (PNNs) is essential to improve its model performance. However, the successively cascading of network hidden layers results in larger integrated photonic chip areas. To address this issue, we propose the optical neural ordinary differential equations (ON-ODE) architecture that parameterizes the continuous dynamics of hidden layers with optical ODE solvers. The ON-ODE comprises the PNNs followed by the photonic integrator and optical feedback loop, which can be configured to represent residual neural networks (ResNet) and recurrent neural networks with effectively reduced chip area occupancy. For the interference-based optoelectronic nonlinear hidden layer, the numerical experiments demonstrate that the single hidden layer ON-ODE can achieve approximately the same accuracy as the two-layer optical ResNet in image classification tasks. Besides, the ONODE improves the model classification accuracy for the diffraction-based all-optical linear hidden layer. The time-dependent dynamics property of ON-ODE is further applied for trajectory prediction with high accuracy.

arXiv:2308.04617공식 코드 · Papers with Code

Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection

Deep neural networks are vulnerable to backdoor attacks (Trojans), where an attacker poisons the training set with backdoor triggers so that the neural network learns to classify test-time triggers to the attacker's designated target class. Recent work shows that backdoor poisoning induces over-fitting (abnormally large activations) in the attacked model, which motivates a general, post-training clipping method for backdoor mitigation, i.e., with bounds on internal-layer activations learned using a small set of clean samples. We devise a new such approach, choosing the activation bounds to explicitly limit classification margins. This method gives superior performance against peer methods for CIFAR-10 image classification. We also show that this method has strong robustness against adaptive attacks, X2X attacks, and on different datasets. Finally, we demonstrate a method extension for test-time detection and correction based on the output differences between the original and activation-bounded networks. The code of our method is online available.