paper-with-me

Papers

Unity is Strength: Unifying Convolutional and Transformeral Features for Better Person Re-Identification

2024-12-23 · Yuhao Wang, Pingping Zhang, Xuehu Liu, Zhengzheng Tu, Huchuan Lu

Person Re-identification (ReID) aims to retrieve the specific person across non-overlapping cameras, which greatly helps intelligent transportation systems. As we all know, Convolutional Neural Networks (CNNs) and Transformers have the unique strengths to extract local and global features, respectively. Considering this fact, we focus on the mutual fusion between them to learn more comprehensive representations for persons. In particular, we utilize the complementary integration of deep features from different model structures. We propose a novel fusion framework called FusionReID to unify the strengths of CNNs and Transformers for image-based person ReID. More specifically, we first deploy a Dual-branch Feature Extraction (DFE) to extract features through CNNs and Transformers from a single image. Moreover, we design a novel Dual-attention Mutual Fusion (DMF) to achieve sufficient feature fusions. The DMF comprises Local Refinement Units (LRU) and Heterogenous Transmission Modules (HTM). LRU utilizes depth-separable convolutions to align deep features in channel dimensions and spatial sizes. HTM consists of a Shared Encoding Unit (SEU) and two Mutual Fusion Units (MFU). Through the continuous stacking of HTM, deep features after LRU are repeatedly utilized to generate more discriminative features. Extensive experiments on three public ReID benchmarks demonstrate that our method can attain superior performances than most state-of-the-arts. The source code is available at https://github.com/924973292/FusionReID.

📄 PDF Abstract BibTeX arXiv:2412.17239

Code (1)

924973292/fusionreid 공식 구현 pytorch

Tasks

Person Re-IdentificationUnity

Methods 이 논문이 사용한 방법론

Focus 설명 없음
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

When Naive Bayes Nearest Neighbors Meet Convolutional Neural Networks

2016-06-01 · CVPR 2016 6 · Ilja Kuzborskij, Fabio Maria Carlucci, Barbara Caputo

Since Convolutional Neural Networks (CNNs) have become the leading learning paradigm in visual recognition, Naive Bayes Nearest Neighbor (NBNN)-based classifiers have lost momentum in the community. This is because (1) s…

Domain Adaptation

When Naïve Bayes Nearest Neighbours Meet Convolutional Neural Networks

2015-11-12 · Ilja Kuzborskij, Fabio Maria Carlucci, Barbara Caputo

Since Convolutional Neural Networks (CNNs) have become the leading learning paradigm in visual recognition, Naive Bayes Nearest Neighbour (NBNN)-based classifiers have lost momentum in the community. This is because (1) …

Domain Adaptation

Context-Aware Learning using Transferable Features for Classification of Breast Cancer Histology Images

2018-02-12 · Ruqayya Awan, Navid Alemi Koohbanani, Muhammad Shaban, Anna Lisowska 외

Convolutional neural networks (CNNs) have been recently used for a variety of histology image analysis. However, availability of a large dataset is a major prerequisite for training a CNN which limits its use by the comp…

Cancer ClassificationClassificationClassification Of Breast Cancer Histology ImagesGeneral Classification

ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks

2019-08-11 · ICCV 2019 10 · Xiaohan Ding, Yuchen Guo, Guiguang Ding, Jungong Han

As designing appropriate Convolutional Neural Network (CNN) architecture in the context of a given application usually involves heavy human works or numerous GPU hours, the research community is soliciting the architectu…

AttributeGPU

CSGCL: Community-Strength-Enhanced Graph Contrastive Learning

2023-05-08 · Han Chen, Ziwen Zhao, Yuhua Li, Yixiong Zou 외

Graph Contrastive Learning (GCL) is an effective way to learn generalized graph representations in a self-supervised manner, and has grown rapidly in recent years. However, the underlying community semantics has not been…

AttributeContrastive LearningLink PredictionNode Classification+1