PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2209.02109공식 코드 · Papers with Code

SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization

Over the past few years, a significant progress has been made in deep convolutional neural networks (CNNs)-based image recognition. This is mainly due to the strong ability of such networks in mining discriminative object pose and parts information from texture and shape. This is often inappropriate for fine-grained visual classification (FGVC) since it exhibits high intra-class and low inter-class variances due to occlusions, deformation, illuminations, etc. Thus, an expressive feature representation describing global structural information is a key to characterize an object/ scene. To this end, we propose a method that effectively captures subtle changes by aggregating context-aware features from most relevant image-regions and their importance in discriminating fine-grained categories avoiding the bounding-box and/or distinguishable part annotations. Our approach is inspired by the recent advancement in self-attention and graph neural networks (GNNs) approaches to include a simple yet effective relation-aware feature transformation and its refinement using a context-aware attention mechanism to boost the discriminability of the transformed feature in an end-to-end learning process. Our model is evaluated on eight benchmark datasets consisting of fine-grained objects and human-object interactions. It outperforms the state-of-the-art approaches by a significant margin in recognition accuracy.

arXiv:2308.13649

Efficient Annotation for Medical Image Analysis: A One-Pass Selective Annotation Approach

Annotating biomedical images for supervised learning is a complex and labor-intensive task due to data diversity and its intricate nature. In this paper, we propose an innovative method, the efficient one-pass selective annotation (EPOSA), that significantly reduces the annotation burden while maintaining robust model performance. Our approach employs a variational autoencoder (VAE) to extract salient features from unannotated images, which are subsequently clustered using the DBSCAN algorithm. This process groups similar images together, forming distinct clusters. We then use a two-stage sample selection algorithm, called representative selection (RepSel), to form a selected dataset. The first stage is a Markov Chain Monte Carlo (MCMC) sampling technique to select representative samples from each cluster for annotations. This selection process is the second stage, which is guided by the principle of maximizing intra-cluster mutual information and minimizing inter-cluster mutual information. This ensures a diverse set of features for model training and minimizes outlier inclusion. The selected samples are used to train a VGG-16 network for image classification. Experimental results on the Med-MNIST dataset demonstrate that our proposed EPOSA outperforms random selection and other state-of-the-art methods under the same annotation budget, presenting a promising direction for efficient and effective annotation in medical image analysis.

arXiv:2311.00548공식 코드 · Papers with Code

Continual atlas-based segmentation of prostate MRI

Continual learning (CL) methods designed for natural image classification often fail to reach basic quality standards for medical image segmentation. Atlas-based segmentation, a well-established approach in medical imaging, incorporates domain knowledge on the region of interest, leading to semantically coherent predictions. This is especially promising for CL, as it allows us to leverage structural information and strike an optimal balance between model rigidity and plasticity over time. When combined with privacy-preserving prototypes, this process offers the advantages of rehearsal-based CL without compromising patient privacy. We propose Atlas Replay, an atlas-based segmentation approach that uses prototypes to generate high-quality segmentation masks through image registration that maintain consistency even as the training distribution changes. We explore how our proposed method performs compared to state-of-the-art CL methods in terms of knowledge transferability across seven publicly available prostate segmentation datasets. Prostate segmentation plays a vital role in diagnosing prostate cancer, however, it poses challenges due to substantial anatomical variations, benign structural differences in older age groups, and fluctuating acquisition parameters. Our results show that Atlas Replay is both robust and generalizes well to yet-unseen domains while being able to maintain knowledge, unlike end-to-end segmentation methods. Our code base is available under https://github.com/MECLabTUDA/Atlas-Replay.

arXiv:2405.00876

Beyond Human Vision: The Role of Large Vision Language Models in Microscope Image Analysis

Vision language models (VLMs) have recently emerged and gained the spotlight for their ability to comprehend the dual modality of image and textual data. VLMs such as LLaVA, ChatGPT-4, and Gemini have recently shown impressive performance on tasks such as natural image captioning, visual question answering (VQA), and spatial reasoning. Additionally, a universal segmentation model by Meta AI, Segment Anything Model (SAM) shows unprecedented performance at isolating objects from unforeseen images. Since medical experts, biologists, and materials scientists routinely examine microscopy or medical images in conjunction with textual information in the form of captions, literature, or reports, and draw conclusions of great importance and merit, it is indubitably essential to test the performance of VLMs and foundation models such as SAM, on these images. In this study, we charge ChatGPT, LLaVA, Gemini, and SAM with classification, segmentation, counting, and VQA tasks on a variety of microscopy images. We observe that ChatGPT and Gemini are impressively able to comprehend the visual features in microscopy images, while SAM is quite capable at isolating artefacts in a general sense. However, the performance is not close to that of a domain expert - the models are readily encumbered by the introduction of impurities, defects, artefact overlaps and diversity present in the images.

arXiv:2410.10382공식 코드 · Papers with Code

V2M: Visual 2-Dimensional Mamba for Image Representation Learning

Mamba has garnered widespread attention due to its flexible design and efficient hardware performance to process 1D sequences based on the state space model (SSM). Recent studies have attempted to apply Mamba to the visual domain by flattening 2D images into patches and then regarding them as a 1D sequence. To compensate for the 2D structure information loss (e.g., local similarity) of the original image, most existing methods focus on designing different orders to sequentially process the tokens, which could only alleviate this issue to some extent. In this paper, we propose a Visual 2-Dimensional Mamba (V2M) model as a complete solution, which directly processes image tokens in the 2D space. We first generalize SSM to the 2-dimensional space which generates the next state considering two adjacent states on both dimensions (e.g., columns and rows). We then construct our V2M based on the 2-dimensional SSM formulation and incorporate Mamba to achieve hardware-efficient parallel processing. The proposed V2M effectively incorporates the 2D locality prior yet inherits the efficiency and input-dependent scalability of Mamba. Extensive experimental results on ImageNet classification and downstream visual tasks including object detection and instance segmentation on COCO and semantic segmentation on ADE20K demonstrate the effectiveness of our V2M compared with other visual backbones.

arXiv:1805.06082

Optical Neural Networks

We develop a novel optical neural network (ONN) framework which introduces a degree of scalar invariance to image classification estima- tion. Taking a hint from the human eye, which has higher resolution near the center of the retina, images are broken out into multiple levels of varying zoom based on a focal point. Each level is passed through an identical convolutional neural network (CNN) in a Siamese fashion, and the results are recombined to produce a high accuracy estimate of the object class. ONNs act as a wrapper around existing CNNs, and can thus be applied to many existing algorithms to produce notable accuracy improvements without having to change the underlying architecture.

arXiv:1803.01947

Segmentation of Drosophila Heart in Optical Coherence Microscopy Images Using Convolutional Neural Networks

Convolutional neural networks are powerful tools for image segmentation and classification. Here, we use this method to identify and mark the heart region of Drosophila at different developmental stages in the cross-sectional images acquired by a custom optical coherence microscopy (OCM) system. With our well-trained convolutional neural network model, the heart regions through multiple heartbeat cycles can be marked with an intersection over union (IOU) of ~86%. Various morphological and dynamical cardiac parameters can be quantified accurately with automatically segmented heart regions. This study demonstrates an efficient heart segmentation method to analyze OCM images of the beating heart in Drosophila.

arXiv:1604.05377

Churn analysis using deep convolutional neural networks and autoencoders

Customer temporal behavioral data was represented as images in order to perform churn prediction by leveraging deep learning architectures prominent in image classification. Supervised learning was performed on labeled data of over 6 million customers using deep convolutional neural networks, which achieved an AUC of 0.743 on the test dataset using no more than 12 temporal features for each customer. Unsupervised learning was conducted using autoencoders to better understand the reasons for customer churn. Images that maximally activate the hidden units of an autoencoder trained with churned customers reveal ample opportunities for action to be taken to prevent churn among strong data, no voice users.

arXiv:1810.03068

Geometric Scattering for Graph Data Analysis

We explore the generalization of scattering transforms from traditional (e.g., image or audio) signals to graph data, analogous to the generalization of ConvNets in geometric deep learning, and the utility of extracted graph features in graph data analysis. In particular, we focus on the capacity of these features to retain informative variability and relations in the data (e.g., between individual graphs, or in aggregate), while relating our construction to previous theoretical results that establish the stability of similar transforms to families of graph deformations. We demonstrate the application the our geometric scattering features in graph classification of social network data, and in data exploration of biochemistry data.

arXiv:1906.11942

Datasets for Face and Object Detection in Fisheye Images

We present two new fisheye image datasets for training face and object detection models: VOC-360 and Wider-360. The fisheye images are created by post-processing regular images collected from two well-known datasets, VOC2012 and Wider Face, using a model for mapping regular to fisheye images implemented in Matlab. VOC-360 contains 39,575 fisheye images for object detection, segmentation, and classification. Wider-360 contains 63,897 fisheye images for face detection. These datasets will be useful for developing face and object detectors as well as segmentation modules for fisheye images while the efforts to collect and manually annotate true fisheye images are underway.

arXiv:2006.08437공식 코드 · Papers with Code

Depth Uncertainty in Neural Networks

Existing methods for estimating uncertainty in deep learning tend to require multiple forward passes, making them unsuitable for applications where computational resources are limited. To solve this, we perform probabilistic reasoning over the depth of neural networks. Different depths correspond to subnetworks which share weights and whose predictions are combined via marginalisation, yielding model uncertainty. By exploiting the sequential structure of feed-forward networks, we are able to both evaluate our training objective and make predictions with a single forward pass. We validate our approach on real-world regression and image classification tasks. Our approach provides uncertainty calibration, robustness to dataset shift, and accuracies competitive with more computationally expensive baselines.

arXiv:2108.10612공식 코드 · Papers with Code

ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classification

Multiple Instance Learning (MIL) gains popularity in many real-life machine learning applications due to its weakly supervised nature. However, the corresponding effort on explaining MIL lags behind, and it is usually limited to presenting instances of a bag that are crucial for a particular prediction. In this paper, we fill this gap by introducing ProtoMIL, a novel self-explainable MIL method inspired by the case-based reasoning process that operates on visual prototypes. Thanks to incorporating prototypical features into objects description, ProtoMIL unprecedentedly joins the model accuracy and fine-grained interpretability, which we present with the experiments on five recognized MIL datasets.

arXiv:2202.07432

A precortical module for robust CNNs to light variations

We present a simple mathematical model for the mammalian low visual pathway, taking into account its key elements: retina, lateral geniculate nucleus (LGN), primary visual cortex (V1). The analogies between the cortical level of the visual system and the structure of popular CNNs, used in image classification tasks, suggests the introduction of an additional preliminary convolutional module inspired to precortical neuronal circuits to improve robustness with respect to global light intensity and contrast variations in the input images. We validate our hypothesis on the popular databases MNIST, FashionMNIST and SVHN, obtaining significantly more robust CNNs with respect to these variations, once such extra module is added.

arXiv:2305.00104

MMViT: Multiscale Multiview Vision Transformers

We present Multiscale Multiview Vision Transformers (MMViT), which introduces multiscale feature maps and multiview encodings to transformer models. Our model encodes different views of the input signal and builds several channel-resolution feature stages to process the multiple views of the input at different resolutions in parallel. At each scale stage, we use a cross-attention block to fuse information across different views. This enables the MMViT model to acquire complex high-dimensional representations of the input at different resolutions. The proposed model can serve as a backbone model in multiple domains. We demonstrate the effectiveness of MMViT on audio and image classification tasks, achieving state-of-the-art results.

arXiv:2608.20712v1cs.CR

Vision Transformer 기반 모델을 위한 프라이버시 보존 객체 검출

Privacy-Preserving Object Detection for Vision Transformer-Based Models

우리는 테스트 이미지의 민감한 시각 정보를 보호할 수 있게 하는 새로운 객체 검출 방법을 제안한다. 시각 정보 보호를 다룬 선행 연구는 주로 이미지 분류 작업에 초점을 맞추어 왔다. 본 논문은 최초로 지각적 암호화(perceptual encryption)를 이용한 객체 검출 방법을 제안한다. 제안 방법은 Vision Transformer(ViT)의 임베딩 구조와 키를 활용한 도메인 적응(domain adaptation) 기법을 이용하여, 어떠한 보호도 적용하지 않은 모델과 거의 동일한 정확도를 달성할 수 있다. 실험에서는 ViT 기반 객체 검출 모델인 ViTdet을 사용하여, 정확도와 시각적 보호 측면에서 제안 방법의 유효성을 검증하였다.

arXiv:1707.01217공식 코드 · Papers with Code

Wasserstein Distance Guided Representation Learning for Domain Adaptation

Domain adaptation aims at generalizing a high-performance learner on a target domain via utilizing the knowledge distilled from a source domain which has a different but related data distribution. One solution to domain adaptation is to learn domain invariant feature representations while the learned representations should also be discriminative in prediction. To learn such representations, domain adaptation frameworks usually include a domain invariant representation learning approach to measure and reduce the domain discrepancy, as well as a discriminator for classification. Inspired by Wasserstein GAN, in this paper we propose a novel approach to learn domain invariant feature representations, namely Wasserstein Distance Guided Representation Learning (WDGRL). WDGRL utilizes a neural network, denoted by the domain critic, to estimate empirical Wasserstein distance between the source and target samples and optimizes the feature extractor network to minimize the estimated Wasserstein distance in an adversarial manner. The theoretical advantages of Wasserstein distance for domain adaptation lie in its gradient property and promising generalization bound. Empirical studies on common sentiment and image classification adaptation datasets demonstrate that our proposed WDGRL outperforms the state-of-the-art domain invariant representation learning approaches.

arXiv:1904.04850

A Non-linear Differential CNN-Rendering Module for 3D Data Enhancement

In this work we introduce a differential rendering module which allows neural networks to efficiently process cluttered data. The module is composed of continuous piecewise differentiable functions defined as a sensor array of cells embedded in 3D space. Our module is learnable and can be easily integrated into neural networks allowing to optimize data rendering towards specific learning tasks using gradient based methods in an end-to-end fashion. Essentially, the module's sensor cells are allowed to transform independently and locally focus and sense different parts of the 3D data. Thus, through their optimization process, cells learn to focus on important parts of the data, bypassing occlusions, clutter and noise. Since sensor cells originally lie on a grid, this equals to a highly non-linear rendering of the scene into a 2D image. Our module performs especially well in presence of clutter and occlusions. Similarly, it deals well with non-linear deformations and improves classification accuracy through proper rendering of the data. In our experiments, we apply our module to demonstrate efficient localization and classification tasks in cluttered data both 2D and 3D.

arXiv:1904.12426

Mixture of Pre-processing Experts Model for Noise Robust Deep Learning on Resource Constrained Platforms

Deep learning on an edge device requires energy efficient operation due to ever diminishing power budget. Intentional low quality data during the data acquisition for longer battery life, and natural noise from the low cost sensor degrade the quality of target output which hinders adoption of deep learning on an edge device. To overcome these problems, we propose simple yet efficient mixture of pre-processing experts (MoPE) model to handle various image distortions including low resolution and noisy images. We also propose to use adversarially trained auto encoder as a pre-processing expert for the noisy images. We evaluate our proposed method for various machine learning tasks including object detection on MS-COCO 2014 dataset, multiple object tracking problem on MOT-Challenge dataset, and human activity classification on UCF 101 dataset. Experimental results show that the proposed method achieves better detection, tracking and activity classification accuracies under noise without sacrificing accuracies for the clean images. The overheads of our proposed MoPE are 0.67% and 0.17% in terms of memory and computation compared to the baseline object detection network.

arXiv:2002.02176

GIM: Gaussian Isolation Machines

In many cases, neural network classifiers are likely to be exposed to input data that is outside of their training distribution data. Samples from outside the distribution may be classified as an existing class with high probability by softmax-based classifiers; such incorrect classifications affect the performance of the classifiers and the applications/systems that depend on them. Previous research aimed at distinguishing training distribution data from out-of-distribution data (OOD) has proposed detectors that are external to the classification method. We present Gaussian isolation machine (GIM), a novel hybrid (generative-discriminative) classifier aimed at solving the problem arising when OOD data is encountered. The GIM is based on a neural network and utilizes a new loss function that imposes a distribution on each of the trained classes in the neural network's output space, which can be approximated by a Gaussian. The proposed GIM's novelty lies in its discriminative performance and generative capabilities, a combination of characteristics not usually seen in a single classifier. The GIM achieves state-of-the-art classification results on image recognition and sentiment analysis benchmarking datasets and can also deal with OOD inputs.

arXiv:2007.05055

SARS-CoV-2 virus RNA sequence classification and geographical analysis with convolutional neural networks approach

Covid-19 infection, which spread to the whole world in December 2019 and is still active, caused more than 250 thousand deaths in the world today. Researches on this subject have been focused on analyzing the genetic structure of the virus, developing vaccines, the course of the disease, and its source. In this study, RNA sequences belonging to the SARS-CoV-2 virus are transformed into gene motifs with two basic image processing algorithms and classified with the convolutional neural network (CNN) models. The CNN models achieved an average of 98% Area Under Curve(AUC) value was achieved in RNA sequences classified as Asia, Europe, America, and Oceania. The resulting artificial neural network model was used for phylogenetic analysis of the variant of the virus isolated in Turkey. The classification results reached were compared with gene alignment values in the GISAID database, where SARS-CoV-2 virus records are kept all over the world. Our experimental results have revealed that now the detection of the geographic distribution of the virus with the CNN models might serve as an efficient method.