PyTorchKR Papers

“Image Classification”

총 18,385편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2405.17824

mTREE: Multi-Level Text-Guided Representation End-to-End Learning for Whole Slide Image Analysis

Multi-modal learning adeptly integrates visual and textual data, but its application to histopathology image and text analysis remains challenging, particularly with large, high-resolution images like gigapixel Whole Slide Images (WSIs). Current methods typically rely on manual region labeling or multi-stage learning to assemble local representations (e.g., patch-level) into global features (e.g., slide-level). However, there is no effective way to integrate multi-scale image representations with text data in a seamless end-to-end process. In this study, we introduce Multi-Level Text-Guided Representation End-to-End Learning (mTREE). This novel text-guided approach effectively captures multi-scale WSI representations by utilizing information from accompanying textual pathology information. mTREE innovatively combines - the localization of key areas (global-to-local) and the development of a WSI-level image-text representation (local-to-global) - into a unified, end-to-end learning framework. In this model, textual information serves a dual purpose: firstly, functioning as an attention map to accurately identify key areas, and secondly, acting as a conduit for integrating textual features into the comprehensive representation of the image. Our study demonstrates the effectiveness of mTREE through quantitative analyses in two image-related tasks: classification and survival prediction, showcasing its remarkable superiority over baselines.

arXiv:1512.02949공식 코드 · Papers with Code

Video captioning with recurrent networks based on frame- and video-level features and visual content classification

In this paper, we describe the system for generating textual descriptions of short video clips using recurrent neural networks (RNN), which we used while participating in the Large Scale Movie Description Challenge 2015 in ICCV 2015. Our work builds on static image captioning systems with RNN based language models and extends this framework to videos utilizing both static image features and video-specific features. In addition, we study the usefulness of visual content classifiers as a source of additional information for caption generation. With experimental results we show that utilizing keyframe based features, dense trajectory video features and content classifier outputs together gives better performance than any one of them individually.

arXiv:1810.12155

Recurrent Transformer Networks for Semantic Correspondence

We present recurrent transformer networks (RTNs) for obtaining dense correspondences between semantically similar images. Our networks accomplish this through an iterative process of estimating spatial transformations between the input images and using these transformations to generate aligned convolutional activations. By directly estimating the transformations between an image pair, rather than employing spatial transformer networks to independently normalize each individual image, we show that greater accuracy can be achieved. This process is conducted in a recursive manner to refine both the transformation estimates and the feature representations. In addition, a technique is presented for weakly-supervised training of RTNs that is based on a proposed classification loss. With RTNs, state-of-the-art performance is attained on several benchmarks for semantic correspondence.

arXiv:1907.03591공식 코드 · Papers with Code

Feature-Based Image Clustering and Segmentation Using Wavelets

Pixel intensity is a widely used feature for clustering and segmentation algorithms, the resulting segmentation using only intensity values might suffer from noises and lack of spatial context information. Wavelet transform is often used for image denoising and classification. We proposed a novel method to incorporate Wavelet features in segmentation and clustering algorithms. The conventional K-means, Fuzzy c-means (FCM), and Active contour without edges (ACWE) algorithms were modified to adapt Wavelet features, leading to robust clustering/segmentation algorithms. A weighting parameter to control the weight of low-frequency sub-band information was also introduced. The new algorithms showed the capability to converge to different segmentation results based on the frequency information derived from the Wavelet sub-bands.

arXiv:2111.13176공식 코드 · Papers with Code

Using Color To Identify Insider Threats

Insider threats are costly, hard to detect, and unfortunately rising in occurrence. Seeking to improve detection of such threats, we develop novel techniques to enable us to extract powerful features and augment attack vectors for greater classification power. Most importantly, we generate high quality color image encodings of user behavior that do not have the downsides of traditional greyscale image encodings. Combined, they form Computer Vision User and Entity Behavior Analytics, a detection system designed from the ground up to improve upon advancements in academia and mitigate the issues that prevent the usage of advanced models in industry. The proposed system beats state-of-art methods used in academia and as well as in industry on a gold standard benchmarking dataset.

arXiv:2406.04624

Image Processing Based Forest Fire Detection

A novel approach for forest fire detection using image processing technique is proposed. A rule-based color model for fire pixel classification is used. The proposed algorithm uses RGB and YCbCr color space. The advantage of using YCbCr color space is that it can separate the luminance from the chrominance more effectively than RGB color space. The performance of the proposed algorithm is tested on two sets of images, one of which contains fire; the other contains fire-like regions. Standard methods are used for calculating the performance of the algorithm. The proposed method has both higher detection rate and lower false alarm rate. Since the algorithm is cheap in computation, it can be used for real-time forest fire detection.

arXiv:2406.16513

Multi-Modal Vision Transformers for Crop Mapping from Satellite Image Time Series

Using images acquired by different satellite sensors has shown to improve classification performance in the framework of crop mapping from satellite image time series (SITS). Existing state-of-the-art architectures use self-attention mechanisms to process the temporal dimension and convolutions for the spatial dimension of SITS. Motivated by the success of purely attention-based architectures in crop mapping from single-modal SITS, we introduce several multi-modal multi-temporal transformer-based architectures. Specifically, we investigate the effectiveness of Early Fusion, Cross Attention Fusion and Synchronized Class Token Fusion within the Temporo-Spatial Vision Transformer (TSViT). Experimental results demonstrate significant improvements over state-of-the-art architectures with both convolutional and self-attention components.

arXiv:2603.15403v2cs.CV

포인팅 기반 객체 인식

Pointing-Based Object Recognition

이 논문은 RGB 이미지를 사용하여 사람의 포인팅 제스처로 지목된 객체를 인식하기 위한 포괄적인 파이프라인을 제시한다. 휴먼-로봇 상호작용이 더 직관적인 인터페이스를 향해 발전함에 따라, 비언어적 의사소통의 대상을 식별하는 능력이 중요해진다. 제안하는 시스템은 객체 검출, 신체 자세 추정, 단안 깊이 추정, 비전-언어 모델을 포함한 여러 기존 최첨단 방법들을 통합한다. 단일 이미지에서 재구성된 3D 공간 정보의 영향과 분류 오류를 수정하는 데 있어 이미지 캡셔닝 모델의 유용성을 평가한다. 맞춤형 데이터셋에 대한 실험 결과, 깊이 정보를 통합하면 특히 겹치는 객체가 있는 복잡한 장면에서 대상 식별이 크게 향상됨을 보여준다. 이 접근법의 모듈성 덕분에 전용 깊이 센서를 사용할 수 없는 환경에서도 배포할 수 있다.

arXiv:2112.14757공식 코드 · Papers with Code

A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model

Recently, open-vocabulary image classification by vision language pre-training has demonstrated incredible achievements, that the model can classify arbitrary categories without seeing additional annotated images of that category. However, it is still unclear how to make the open-vocabulary recognition work well on broader vision problems. This paper targets open-vocabulary semantic segmentation by building it on an off-the-shelf pre-trained vision-language model, i.e., CLIP. However, semantic segmentation and the CLIP model perform on different visual granularity, that semantic segmentation processes on pixels while CLIP performs on images. To remedy the discrepancy in processing granularity, we refuse the use of the prevalent one-stage FCN based framework, and advocate a two-stage semantic segmentation framework, with the first stage extracting generalizable mask proposals and the second stage leveraging an image based CLIP model to perform open-vocabulary classification on the masked image crops which are generated in the first stage. Our experimental results show that this two-stage framework can achieve superior performance than FCN when trained only on COCO Stuff dataset and evaluated on other datasets without fine-tuning. Moreover, this simple framework also surpasses previous state-of-the-arts of zero-shot semantic segmentation by a large margin: +29.5 hIoU on the Pascal VOC 2012 dataset, and +8.9 hIoU on the COCO Stuff dataset. With its simplicity and strong performance, we hope this framework to serve as a baseline to facilitate future research. The code are made publicly available at~\url{https://github.com/MendelXu/zsseg.baseline}.

arXiv:2401.09823

Enhancing Small Object Encoding in Deep Neural Networks: Introducing Fast&Focused-Net with Volume-wise Dot Product Layer

In this paper, we introduce Fast&Focused-Net, a novel deep neural network architecture tailored for efficiently encoding small objects into fixed-length feature vectors. Contrary to conventional Convolutional Neural Networks (CNNs), Fast&Focused-Net employs a series of our newly proposed layer, the Volume-wise Dot Product (VDP) layer, designed to address several inherent limitations of CNNs. Specifically, CNNs often exhibit a smaller effective receptive field than their theoretical counterparts, limiting their vision span. Additionally, the initial layers in CNNs produce low-dimensional feature vectors, presenting a bottleneck for subsequent learning. Lastly, the computational overhead of CNNs, particularly in capturing diverse image regions by parameter sharing, is significantly high. The VDP layer, at the heart of Fast&Focused-Net, aims to remedy these issues by efficiently covering the entire image patch information with reduced computational demand. Experimental results demonstrate the prowess of Fast&Focused-Net in a variety of applications. For small object classification tasks, our network outperformed state-of-the-art methods on datasets such as CIFAR-10, CIFAR-100, STL-10, SVHN-Cropped, and Fashion-MNIST. In the context of larger image classification, when combined with a transformer encoder (ViT), Fast&Focused-Net produced competitive results for OpenImages V6, ImageNet-1K, and Places365 datasets. Moreover, the same combination showcased unparalleled performance in text recognition tasks across SVT, IC15, SVTP, and HOST datasets. This paper presents the architecture, the underlying motivation, and extensive empirical evidence suggesting that Fast&Focused-Net is a promising direction for efficient and focused deep learning.

arXiv:2406.14566

LM-IGTD: a 2D image generator for low-dimensional and mixed-type tabular data to leverage the potential of convolutional neural networks

Tabular data have been extensively used in different knowledge domains. Convolutional neural networks (CNNs) have been successfully used in many applications where important information about data is embedded in the order of features (images), outperforming predictive results of traditional models. Recently, several researchers have proposed transforming tabular data into images to leverage the potential of CNNs and obtain high results in predictive tasks such as classification and regression. In this paper, we present a novel and effective approach for transforming tabular data into images, addressing the inherent limitations associated with low-dimensional and mixed-type datasets. Our method, named Low Mixed-Image Generator for Tabular Data (LM-IGTD), integrates a stochastic feature generation process and a modified version of the IGTD. We introduce an automatic and interpretable end-to-end pipeline, enabling the creation of images from tabular data. A mapping between original features and the generated images is established, and post hoc interpretability methods are employed to identify crucial areas of these images, enhancing interpretability for predictive tasks. An extensive evaluation of the tabular-to-image generation approach proposed on 12 low-dimensional and mixed-type datasets, including binary and multi-class classification scenarios. In particular, our method outperformed all traditional ML models trained on tabular data in five out of twelve datasets when using images generated with LM-IGTD and CNN. In the remaining datasets, LM-IGTD images and CNN consistently surpassed three out of four traditional ML models, achieving similar results to the fourth model.

arXiv:2610.13780v1cs.CV

형광 현미경 이미지에서 극히 희귀한 사멸 세포의 검출

Detection of extremely rare dead cells in fluorescence microscopy images

형광 현미경 관찰에서 사멸 세포 검출은 표현형 스크리닝과 약물 효능 평가에 필수적입니다. 그러나 신호 가변성, 광학 인공물(optical artifact), 여러 채널 간 공국재화(colocalization) 모호성으로 인해 자동 식별은 여전히 어렵습니다. 세포핵 경계를 정의하는 마커는 세포사멸(apoptotic) 마커와 공간적 또는 시간적으로 깔끔하게 일치하지 않습니다. 더욱이 마커 축적 동역학은 개별 세포 및 세포사멸 단계마다 다르므로 범용 임계값을 신뢰하기 어렵습니다. 본 논문에서는 핵 염색 검체에서 세포사멸 세포를 검출하기 위한 여러 전산적 접근 방식에 대한 체계적인 비교를 제시합니다: (1) 강도 임계값, 분포, 상관관계 및 도메인 지침을 사용하는 휴리스틱 방법; (2) 수치적 특징(로지스틱 회귀, 랜덤 포레스트, XGBoost 및 LightGBM)과 이미지 특징(ResNet-18 및 EfficientNet-B0)을 사용하는 분류; (3) 마찬가지로 수치적 특징(격리 포레스트, 원클래스 SVM 및 PCA 재구성)과 이미지 특징(합성곱 오토인코더 및 Deep SVDD)을 사용하는 이상 탐지. 수작업으로 주석이 달린 243개의 실측값(ground truth) 사멸 세포를 포함하여 여러 장면에 걸쳐 65,527개의 세포/핵이 포함된 258개 이미지 데이터셋을 사용하여, PR-AUC, 정밀도, 재현율, F1-score 및 macro-F1과 같은 지표로 각 방법을 평가합니다. 연구 결과에 따르면 이미지 특징을 사용하는 분류(심층 학습)와 수치적 특징을 사용하는 분류(전통적 방식)가 가장 우수한 성능을 달성했으며, ResNet-18과 XGBoost가 수작업으로 설계된 휴리스틱 및 이상 탐지 방법보다 크게 우수한 성과를 보였습니다. 이러한 연구 결과는 최첨단 전산 및 학습 기법으로도 이러한 생의학 문제를 해결하는 것이 여전히 매우 까다롭다는 점을 보여줍니다. 우리는 도메인 과학자를 돕는 보조 도구로서 완전 자동 방식이나 인간 참여형(human-in-the-loop) 설정 모두에서 연구자들에게 효과적인 의사결정 지원 도구를 제공하는 것을 목표로 합니다.

arXiv:2102.08012

Training Stacked Denoising Autoencoders for Representation Learning

We implement stacked denoising autoencoders, a class of neural networks that are capable of learning powerful representations of high dimensional data. We describe stochastic gradient descent for unsupervised training of autoencoders, as well as a novel genetic algorithm based approach that makes use of gradient information. We analyze the performance of both optimization algorithms and also the representation learning ability of the autoencoder when it is trained on standard image classification datasets.

arXiv:2103.01292

Maximal function pooling with applications

Inspired by the Hardy-Littlewood maximal function, we propose a novel pooling strategy which is called maxfun pooling. It is presented both as a viable alternative to some of the most popular pooling functions, such as max pooling and average pooling, and as a way of interpolating between these two algorithms. We demonstrate the features of maxfun pooling with two applications: first in the context of convolutional sparse coding, and then for image classification.

arXiv:2212.03709

Development Of A Fire Detection System On Satellite Images

This paper discusses the development of a convolutional architecture of a deep neural network for the recognition of wildfires on satellite images. Based on the results of image classification, a fuzzy cognitive map of the analysis of the macroeconomic situation was built. The paper also considers the prospect of using hybrid cognitive models for forecasting macroeconomic indicators based on fuzzy cognitive maps using data on recognized wildfires on satellite images.

arXiv:2402.11458공식 코드 · Papers with Code

Key Patch Proposer: Key Patches Contain Rich Information

In this paper, we introduce a novel algorithm named Key Patch Proposer (KPP) designed to select key patches in an image without additional training. Our experiments showcase KPP's robust capacity to capture semantic information by both reconstruction and classification tasks. The efficacy of KPP suggests its potential application in active learning for semantic segmentation. Our source code is publicly available at https://github.com/CA-TT-AC/key-patch-proposer.

arXiv:2211.02791

Multi-Objective Evolutionary for Object Detection Mobile Architectures Search

Recently, Neural architecture search has achieved great success on classification tasks for mobile devices. The backbone network for object detection is usually obtained on the image classification task. However, the architecture which is searched through the classification task is sub-optimal because of the gap between the task of image and object detection. As while work focuses on backbone network architecture search for mobile device object detection is limited, mainly because the backbone always requires expensive ImageNet pre-training. Accordingly, it is necessary to study the approach of network architecture search for mobile device object detection without expensive pre-training. In this work, we propose a mobile object detection backbone network architecture search algorithm which is a kind of evolutionary optimized method based on non-dominated sorting for NAS scenarios. It can quickly search to obtain the backbone network architecture within certain constraints. It better solves the problem of suboptimal linear combination accuracy and computational cost. The proposed approach can search the backbone networks with different depths, widths, or expansion sizes via a technique of weight mapping, making it possible to use NAS for mobile devices detection tasks a lot more efficiently. In our experiments, we verify the effectiveness of the proposed approach on YoloX-Lite, a lightweight version of the target detection framework. Under similar computational complexity, the accuracy of the backbone network architecture we search for is 2.0% mAP higher than MobileDet. Our improved backbone network can reduce the computational effort while improving the accuracy of the object detection network. To prove its effectiveness, a series of ablation studies have been carried out and the working mechanism has been analyzed in detail.

arXiv:2007.15422

Few shot domain adaptation for in situ macromolecule structural classification in cryo-electron tomograms

Motivation: Cryo-Electron Tomography (cryo-ET) visualizes structure and spatial organization of macromolecules and their interactions with other subcellular components inside single cells in the close-to-native state at sub-molecular resolution. Such information is critical for the accurate understanding of cellular processes. However, subtomogram classification remains one of the major challenges for the systematic recognition and recovery of the macromolecule structures in cryo-ET because of imaging limits and data quantity. Recently, deep learning has significantly improved the throughput and accuracy of large-scale subtomogram classification. However often it is difficult to get enough high-quality annotated subtomogram data for supervised training due to the enormous expense of labeling. To tackle this problem, it is beneficial to utilize another already annotated dataset to assist the training process. However, due to the discrepancy of image intensity distribution between source domain and target domain, the model trained on subtomograms in source domainmay perform poorly in predicting subtomogram classes in the target domain. Results: In this paper, we adapt a few shot domain adaptation method for deep learning based cross-domain subtomogram classification. The essential idea of our method consists of two parts: 1) take full advantage of the distribution of plentiful unlabeled target domain data, and 2) exploit the correlation between the whole source domain dataset and few labeled target domain data. Experiments conducted on simulated and real datasets show that our method achieves significant improvement on cross domain subtomogram classification compared with baseline methods.

arXiv:1804.08711

All-Optical Machine Learning Using Diffractive Deep Neural Networks

We introduce an all-optical Diffractive Deep Neural Network (D2NN) architecture that can learn to implement various functions after deep learning-based design of passive diffractive layers that work collectively. We experimentally demonstrated the success of this framework by creating 3D-printed D2NNs that learned to implement handwritten digit classification and the function of an imaging lens at terahertz spectrum. With the existing plethora of 3D-printing and other lithographic fabrication methods as well as spatial-light-modulators, this all-optical deep learning framework can perform, at the speed of light, various complex functions that computer-based neural networks can implement, and will find applications in all-optical image analysis, feature detection and object classification, also enabling new camera designs and optical components that can learn to perform unique tasks using D2NNs.

arXiv:1704.04097

Recognizing Activities of Daily Living from Egocentric Images

Recognizing Activities of Daily Living (ADLs) has a large number of health applications, such as characterize lifestyle for habit improvement, nursing and rehabilitation services. Wearable cameras can daily gather large amounts of image data that provide rich visual information about ADLs than using other wearable sensors. In this paper, we explore the classification of ADLs from images captured by low temporal resolution wearable camera (2fpm) by using a Convolutional Neural Networks (CNN) approach. We show that the classification accuracy of a CNN largely improves when its output is combined, through a random decision forest, with contextual information from a fully connected layer. The proposed method was tested on a subset of the NTCIR-12 egocentric dataset, consisting of 18,674 images and achieved an overall accuracy of 86% activity recognition on 21 classes.