Free Lunch for Gait Recognition: A Novel Relation Descriptor

• URL: http://arxiv.org/abs/2308.11487v3
• Date: Tue, 5 Dec 2023 03:37:33 GMT
• Title: Free Lunch for Gait Recognition: A Novel Relation Descriptor
• Authors: Jilong Wang, Saihui Hou, Yan Huang, Chunshui Cao, Xu Liu, Yongzhen Huang, Tianzhu Zhang, Liang Wang
• Abstract summary: We propose a novel $textbfRelation Descriptor$ that captures relations between test gaits and pre-selected gait anchors. We evaluate the effectiveness of our method on the popular GREW, Gait3D, OU-M, CASIA-B, and CCPG.
• Score: 39.01813894844141
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Gait recognition is to seek correct matches for query individuals by their unique walking patterns. However, current methods focus solely on extracting individual-specific features, overlooking ``interpersonal" relationships. In this paper, we propose a novel $\textbf{Relation Descriptor}$ that captures not only individual features but also relations between test gaits and pre-selected gait anchors. Specifically, we reinterpret classifier weights as gait anchors and compute similarity scores between test features and these anchors, which re-expresses individual gait features into a similarity relation distribution. In essence, the relation descriptor offers a holistic perspective that leverages the collective knowledge stored within the classifier's weights, emphasizing meaningful patterns and enhancing robustness. Despite its potential, relation descriptor poses dimensionality challenges since its dimension depends on the training set's identity count. To address this, we propose Farthest gait-Anchor Selection to identify the most discriminative gait anchors and an Orthogonal Regularization Loss to increase diversity within gait anchors. Compared to individual-specific features extracted from the backbone, our relation descriptor can boost the performance nearly without any extra costs. We evaluate the effectiveness of our method on the popular GREW, Gait3D, OU-MVLP, CASIA-B, and CCPG, showing that our method consistently outperforms the baselines and achieves state-of-the-art performance.

Related papers

• Cloned Identity Detection in Social-Sensor Clouds based on Incomplete Profiles [5.411585313453657]
  We propose a novel approach to effectively detect cloned identities of social-sensor cloud service providers (i.e. social media users) in the face of non-privacy-sensitive profile data. Named ICD-IPD, the proposed approach first extracts account pairs with similar usernames or screen names from a given set of user accounts collected from a social media. It then learns a multi-view representation associated with a given account and extracts two categories of features for every single account.
  arXiv  Detail & Related papers  (2024-11-02T18:23:22Z)
• 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)
• Robust Outlier Rejection for 3D Registration with Variational Bayes [70.98659381852787]
  We develop a novel variational non-local network-based outlier rejection framework for robust alignment. We propose a voting-based inlier searching strategy to cluster the high-quality hypothetical inliers for transformation estimation.
  arXiv  Detail & Related papers  (2023-04-04T03:48:56Z)
• FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network [48.912196729711624]
  Few-shot semantic segmentation is the task of learning to locate each pixel of a novel class in a query image with only a few annotated support images. We propose a Feature-Enhanced Context-Aware Network (FECANet) to suppress the matching noise caused by inter-class local similarity. In addition, we propose a novel correlation reconstruction module that encodes extra correspondence relations between foreground and background and multi-scale context semantic features.
  arXiv  Detail & Related papers  (2023-01-19T16:31:13Z)
• An Omnidirectional Approach to Touch-based Continuous Authentication [6.83780085440235]
  This paper focuses on how touch interactions on smartphones can provide a continuous user authentication service through behaviour captured by a touchscreen. We present an omnidirectional approach which outperforms the traditional method independent of the touch direction. We find that the TouchAlytics feature set outperforms others when using our approach when combining three or more strokes.
  arXiv  Detail & Related papers  (2023-01-13T13:58:06Z)
• Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptation [79.62038105814658]
  Universal Domain aims to transfer the knowledge between datasets by handling two shifts: domain-shift and categoryshift. Main challenge is correctly distinguishing the unknown target samples while adapting the distribution of known class knowledge from source to target. Most existing methods approach this problem by first training the target adapted known and then relying on the single threshold to distinguish unknown target samples.
  arXiv  Detail & Related papers  (2022-12-16T09:01:57Z)
• Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification [80.98291772215154]
  Unsupervised person re-identification (ReID) aims at learning discriminative identity features for person retrieval without any annotations. Recent advances accomplish this task by leveraging clustering-based pseudo labels. We propose a Neighbour Consistency guided Pseudo Label Refinement framework.
  arXiv  Detail & Related papers  (2022-11-30T09:39:57Z)
• Annotation Efficient Person Re-Identification with Diverse Cluster-Based Pair Selection [39.61651209527681]
  Person Re-identification (Re-ID) has attracted great attention due to its promising real-world applications. It is always costly to annotate the training data to train a Re-ID model, and it still remains challenging to reduce the annotation cost while maintaining the performance for the Re-ID task. We propose the Efficient Person Re-identification method to select image pairs from an alternative pair set according to the fallibility and diversity of pairs, and train the Re-ID model based on the annotation.
  arXiv  Detail & Related papers  (2022-03-10T14:37:07Z)
• Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels [7.920797564912219]
  We propose an efficient estimation procedure based on a clusterability condition. Compared with methods using anchor points, our approach uses substantially more instances and benefits from a much better sample complexity.
  arXiv  Detail & Related papers  (2021-02-10T07:22:56Z)

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.