Diversity-Achieving Slow-DropBlock Network for Person Re-Identification
- URL: http://arxiv.org/abs/2002.04414v1
- Date: Sun, 9 Feb 2020 08:05:39 GMT
- Title: Diversity-Achieving Slow-DropBlock Network for Person Re-Identification
- Authors: Xiaofu Wu, Ben Xie, Shiliang Zhao, Suofei Zhang, Yong Xiao, Ming Li
- Abstract summary: A big challenge of person re-identification (Re-ID) using a multi-branch network architecture is to learn diverse features from the ID-labeled dataset.
The 2-branch Batch DropBlock (BDB) network was recently proposed for achieving diversity between the global branch and the feature-dropping branch.
We show that the proposed method performs superior to BDB on popular person Re-ID datasets, including Market-1501, DukeMTMC-reID and CUHK03.
- Score: 11.907116133358022
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: A big challenge of person re-identification (Re-ID) using a multi-branch
network architecture is to learn diverse features from the ID-labeled dataset.
The 2-branch Batch DropBlock (BDB) network was recently proposed for achieving
diversity between the global branch and the feature-dropping branch. In this
paper, we propose to move the dropping operation from the intermediate feature
layer towards the input (image dropping). Since it may drop a large portion of
input images, this makes the training hard to converge. Hence, we propose a
novel double-batch-split co-training approach for remedying this problem. In
particular, we show that the feature diversity can be well achieved with the
use of multiple dropping branches by setting individual dropping ratio for each
branch. Empirical evidence demonstrates that the proposed method performs
superior to BDB on popular person Re-ID datasets, including Market-1501,
DukeMTMC-reID and CUHK03 and the use of more dropping branches can further
boost the performance.
Related papers
- Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training [51.87027943520492]
We present a novel paradigm Diffusion-ReID to efficiently augment and generate diverse images based on known identities.
Benefiting from our proposed paradigm, we first create a new large-scale person Re-ID dataset Diff-Person, which consists of over 777K images from 5,183 identities.
arXiv Detail & Related papers (2024-06-10T06:26:03Z) - Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification [64.36210786350568]
We propose a novel learning framework named textbfEDITOR to select diverse tokens from vision Transformers for multi-modal object ReID.
Our framework can generate more discriminative features for multi-modal object ReID.
arXiv Detail & Related papers (2024-03-15T12:44:35Z) - Mutual Distillation Learning For Person Re-Identification [27.350415735863184]
We propose a novel approach, Mutual Distillation Learning For Person Re-identification (termed as MDPR)
Our approach encompasses two branches: a hard content branch to extract local features via a uniform horizontal partitioning strategy and a Soft Content Branch to dynamically distinguish between foreground and background.
Our method achieves an impressive $88.7%/94.4%$ in mAP/Rank-1 on the DukeC-reID dataset, surpassing the current state-of-the-art results.
arXiv Detail & Related papers (2024-01-12T07:49:02Z) - Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification [78.52704557647438]
We propose a novel FIne-grained Representation and Recomposition (FIRe$2$) framework to tackle both limitations without any auxiliary annotation or data.
Experiments demonstrate that FIRe$2$ can achieve state-of-the-art performance on five widely-used cloth-changing person Re-ID benchmarks.
arXiv Detail & Related papers (2023-08-21T12:59:48Z) - Learning to Disentangle Scenes for Person Re-identification [15.378033331385312]
This paper proposes to divide-and-conquer the person re-identification (ReID) task.
We employ several self-supervision operations to simulate different challenging problems and handle each challenging problem using different networks.
A general multi-branch network, including one master branch and two servant branches, is introduced to handle different scenes.
arXiv Detail & Related papers (2021-11-10T01:17:10Z) - HAT: Hierarchical Aggregation Transformers for Person Re-identification [87.02828084991062]
We take advantages of both CNNs and Transformers for image-based person Re-ID with high performance.
Work is the first to take advantages of both CNNs and Transformers for image-based person Re-ID.
arXiv Detail & Related papers (2021-07-13T09:34:54Z) - Decoupled and Memory-Reinforced Networks: Towards Effective Feature
Learning for One-Step Person Search [65.51181219410763]
One-step methods have been developed to handle pedestrian detection and identification sub-tasks using a single network.
There are two major challenges in the current one-step approaches.
We propose a decoupled and memory-reinforced network (DMRNet) to overcome these problems.
arXiv Detail & Related papers (2021-02-22T06:19:45Z) - Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse
Features for Person Re-identification [7.068680287596106]
Deep Miner is a method that allows CNNs to "mine" richer and more diverse features about people.
It produces a model that significantly outperforms state-of-the-art (SOTA) re-identification methods.
arXiv Detail & Related papers (2021-02-18T13:30:23Z) - Camera-aware Proxies for Unsupervised Person Re-Identification [60.26031011794513]
This paper tackles the purely unsupervised person re-identification (Re-ID) problem that requires no annotations.
We propose to split each single cluster into multiple proxies and each proxy represents the instances coming from the same camera.
Based on the camera-aware proxies, we design both intra- and inter-camera contrastive learning components for our Re-ID model.
arXiv Detail & Related papers (2020-12-19T12:37:04Z) - Progressive Multi-stage Feature Mix for Person Re-Identification [11.161336369536818]
CNN suffers from paying too much attention on the most salient local areas.
%BDB proposes to randomly drop one block in a batch to enlarge the high response areas.
We propose a Progressive Multi-stage feature Mix network (PMM), which enables the model to find out the more precise and diverse features in a progressive manner.
arXiv Detail & Related papers (2020-07-17T06:59:39Z) - A heterogeneous branch and multi-level classification network for person
re-identification [13.868524909296553]
We propose a novel Heterogeneous Branch and Multi-level Classification Network (HBMCN), which is designed based on the pre-trained ResNet-50 model.
A new multi-level classification function is proposed for the supervised learning ofCN, whereby multi-level features are extracted from multiple high-level layers and objectived to represent a person.
arXiv Detail & Related papers (2020-06-02T03:34:50Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.