BigGait: Learning Gait Representation You Want by Large Vision Models
- URL: http://arxiv.org/abs/2402.19122v2
- Date: Fri, 22 Mar 2024 07:03:54 GMT
- Title: BigGait: Learning Gait Representation You Want by Large Vision Models
- Authors: Dingqiang Ye, Chao Fan, Jingzhe Ma, Xiaoming Liu, Shiqi Yu,
- Abstract summary: Existing gait recognition methods rely on task-specific upstream driven by supervised learning to provide explicit gait representations.
Escaping from this trend, this work proposes a simple yet efficient gait framework, termed BigGait.
BigGait transforms all-purpose knowledge into implicit gait representations without requiring third-party supervision signals.
- Score: 12.620774996969535
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Gait recognition stands as one of the most pivotal remote identification technologies and progressively expands across research and industry communities. However, existing gait recognition methods heavily rely on task-specific upstream driven by supervised learning to provide explicit gait representations like silhouette sequences, which inevitably introduce expensive annotation costs and potential error accumulation. Escaping from this trend, this work explores effective gait representations based on the all-purpose knowledge produced by task-agnostic Large Vision Models (LVMs) and proposes a simple yet efficient gait framework, termed BigGait. Specifically, the Gait Representation Extractor (GRE) within BigGait draws upon design principles from established gait representations, effectively transforming all-purpose knowledge into implicit gait representations without requiring third-party supervision signals. Experiments on CCPG, CAISA-B* and SUSTech1K indicate that BigGait significantly outperforms the previous methods in both within-domain and cross-domain tasks in most cases, and provides a more practical paradigm for learning the next-generation gait representation. Finally, we delve into prospective challenges and promising directions in LVMs-based gait recognition, aiming to inspire future work in this emerging topic. The source code is available at https://github.com/ShiqiYu/OpenGait.
Related papers
- OpenGait: A Comprehensive Benchmark Study for Gait Recognition towards Better Practicality [11.64292241875791]
We first develop OpenGait, a flexible and efficient gait recognition platform.
Using OpenGait as a foundation, we conduct in-depth ablation experiments to revisit recent developments in gait recognition.
Inspired by these findings, we develop three structurally simple yet empirically powerful and practically robust baseline models.
arXiv Detail & Related papers (2024-05-15T07:11:12Z) - Knowledge Plugins: Enhancing Large Language Models for Domain-Specific
Recommendations [50.81844184210381]
We propose a general paradigm that augments large language models with DOmain-specific KnowledgE to enhance their performance on practical applications, namely DOKE.
This paradigm relies on a domain knowledge extractor, working in three steps: 1) preparing effective knowledge for the task; 2) selecting the knowledge for each specific sample; and 3) expressing the knowledge in an LLM-understandable way.
arXiv Detail & Related papers (2023-11-16T07:09:38Z) - Exploring Incompatible Knowledge Transfer in Few-shot Image Generation [107.81232567861117]
Few-shot image generation learns to generate diverse and high-fidelity images from a target domain using a few reference samples.
Existing F SIG methods select, preserve and transfer prior knowledge from a source generator to learn the target generator.
We propose knowledge truncation, which is a complementary operation to knowledge preservation and is implemented by a lightweight pruning-based method.
arXiv Detail & Related papers (2023-04-15T14:57:15Z) - Exploring Deep Models for Practical Gait Recognition [11.185716724976414]
We present a unified perspective to explore how to construct deep models for state-of-the-art outdoor gait recognition.
Specifically, we challenge the stereotype of shallow gait models and demonstrate the superiority of explicit temporal modeling.
The proposed CNN-based DeepGaitV2 series and Transformer-based SwinGait series exhibit significant performance improvements on Gait3D and GREW.
arXiv Detail & Related papers (2023-03-06T17:19:28Z) - Learning Common Rationale to Improve Self-Supervised Representation for
Fine-Grained Visual Recognition Problems [61.11799513362704]
We propose learning an additional screening mechanism to identify discriminative clues commonly seen across instances and classes.
We show that a common rationale detector can be learned by simply exploiting the GradCAM induced from the SSL objective.
arXiv Detail & Related papers (2023-03-03T02:07:40Z) - Learning Gait Representation from Massive Unlabelled Walking Videos: A
Benchmark [11.948554539954673]
This paper proposes a large-scale self-supervised benchmark for gait recognition with contrastive learning.
We collect a large-scale unlabelled gait dataset GaitLU-1M consisting of 1.02M walking sequences.
We evaluate the pre-trained model on four widely-used gait benchmarks, CASIA-B, OU-M, GREW and Gait3D with or without transfer learning.
arXiv Detail & Related papers (2022-06-28T12:33:42Z) - Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based
Baseline [95.88825497452716]
Gait benchmarks empower the research community to train and evaluate high-performance gait recognition systems.
GREW is the first large-scale dataset for gait recognition in the wild.
SPOSGait is the first NAS-based gait recognition model.
arXiv Detail & Related papers (2022-05-05T14:57:39Z) - HEATGait: Hop-Extracted Adjacency Technique in Graph Convolution based
Gait Recognition [0.0]
HEATGait is a gait recognition system that improves the existing multi-scale convolution graph by efficient hop-extraction technique to alleviate the issue.
We propose a powerful feature extractor that utilizes ResG to achieve state-of-the-art performance in model-based gait recognition on the CASIA-BCN gait dataset.
arXiv Detail & Related papers (2022-04-21T16:13:58Z) - Reinforcement Learning with Prototypical Representations [114.35801511501639]
Proto-RL is a self-supervised framework that ties representation learning with exploration through prototypical representations.
These prototypes simultaneously serve as a summarization of the exploratory experience of an agent as well as a basis for representing observations.
This enables state-of-the-art downstream policy learning on a set of difficult continuous control tasks.
arXiv Detail & Related papers (2021-02-22T18:56:34Z) - TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain
Gait Recognition [77.77786072373942]
This paper proposes a Transferable Neighborhood Discovery (TraND) framework to bridge the domain gap for unsupervised cross-domain gait recognition.
We design an end-to-end trainable approach to automatically discover the confident neighborhoods of unlabeled samples in the latent space.
Our method achieves state-of-the-art results on two public datasets, i.e., CASIA-B and OU-LP.
arXiv Detail & Related papers (2021-02-09T03:07:07Z)
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.