A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition

• URL: http://arxiv.org/abs/2307.15252v1
• Date: Fri, 28 Jul 2023 01:34:55 GMT
• Title: A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition
• Authors: Yibo Zhou, Hai-Miao Hu, Jinzuo Yu, Zhenbo Xu, Weiqing Lu, Yuran Cao
• Abstract summary: We show that current methods can actually suffer in generalizing such fitted attributes interdependencies onto scenes or identities off the dataset distribution. To render models robust in realistic scenes, we propose the attributes-disentangled feature learning to ensure the recognition of an attribute not inferring on the existence of others.
• Score: 10.821982414387525
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent studies on pedestrian attribute recognition progress with either explicit or implicit modeling of the co-occurrence among attributes. Considering that this known a prior is highly variable and unforeseeable regarding the specific scenarios, we show that current methods can actually suffer in generalizing such fitted attributes interdependencies onto scenes or identities off the dataset distribution, resulting in the underlined bias of attributes co-occurrence. To render models robust in realistic scenes, we propose the attributes-disentangled feature learning to ensure the recognition of an attribute not inferring on the existence of others, and which is sequentially formulated as a problem of mutual information minimization. Rooting from it, practical strategies are devised to efficiently decouple attributes, which substantially improve the baseline and establish state-of-the-art performance on realistic datasets like PETAzs and RAPzs. Code is released on https://github.com/SDret/A-Solution-to-Co-occurence-Bias-in-Pedestrian-Attribute-Recognition.

Related papers

• Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks [21.813755593742858]
  Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for classifications. We propose a novel debiasing framework, Debiasing Global Workspace, introducing attention-based information bottlenecks for learning compositional representations of attributes. We conduct comprehensive evaluations on biased datasets, along with both quantitative and qualitative analyses, to showcase our approach's efficacy.
  arXiv  Detail & Related papers  (2024-03-21T05:33:49Z)
• Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrieval [65.43522019468976]
  We propose attribute-aware hashing networks with self-consistency for generating attribute-aware hash codes. We develop an encoder-decoder structure network of a reconstruction task to unsupervisedly distill high-level attribute-specific vectors. Our models are equipped with a feature decorrelation constraint upon these attribute vectors to strengthen their representative abilities.
  arXiv  Detail & Related papers  (2023-11-21T08:20:38Z)
• Causal Effect Regularization: Automated Detection and Removal of Spurious Attributes [13.852987916253685]
  In many classification datasets, the task labels are spuriously correlated with some input attributes. We propose a method to automatically identify spurious attributes by estimating their causal effect on the label. Our method mitigates the reliance on spurious attributes even under noisy estimation of causal effects.
  arXiv  Detail & Related papers  (2023-06-19T17:17:42Z)
• UPAR: Unified Pedestrian Attribute Recognition and Person Retrieval [4.6193503399184275]
  We present UPAR, the Unified Person Attribute Recognition dataset. It is based on four well-known person attribute recognition datasets: PA100k, PETA, RAPv2, and Market1501. We unify those datasets by providing 3,3M additional annotations to harmonize 40 important binary attributes over 12 attribute categories.
  arXiv  Detail & Related papers  (2022-09-06T14:20:56Z)
• TransFA: Transformer-based Representation for Face Attribute Evaluation [87.09529826340304]
  We propose a novel textbftransformer-based representation for textbfattribute evaluation method (textbfTransFA) The proposed TransFA achieves superior performances compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-07-12T10:58:06Z)
• Calibrated Feature Decomposition for Generalizable Person Re-Identification [82.64133819313186]
  Calibrated Feature Decomposition (CFD) module focuses on improving the generalization capacity for person re-identification. A calibrated-and-standardized Batch normalization (CSBN) is designed to learn calibrated person representation.
  arXiv  Detail & Related papers  (2021-11-27T17:12:43Z)
• Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition [50.932864767867365]
  We propose a framework that consists of two complementary regularizations to achieve spatial and semantic consistency for each attribute. Based on the precise attribute locations, we propose a semantic consistency regularization to extract intrinsic and discriminative semantic features. Results show that the proposed method performs favorably against state-of-the-art methods without increasing parameters.
  arXiv  Detail & Related papers  (2021-09-13T03:36:44Z)
• Disentangled Face Attribute Editing via Instance-Aware Latent Space Search [30.17338705964925]
  A rich set of semantic directions exist in the latent space of Generative Adversarial Networks (GANs) Existing methods may suffer poor attribute variation disentanglement, leading to unwanted change of other attributes when altering the desired one. We propose a novel framework (IALS) that performs Instance-Aware Latent-Space Search to find semantic directions for disentangled attribute editing.
  arXiv  Detail & Related papers  (2021-05-26T16:19:08Z)
• AttributeNet: Attribute Enhanced Vehicle Re-Identification [70.89289512099242]
  We introduce AttributeNet (ANet) that jointly extracts identity-relevant features and attribute features. We enable the interaction by distilling the ReID-helpful attribute feature and adding it into the general ReID feature to increase the discrimination power. We validate the effectiveness of our framework on three challenging datasets.
  arXiv  Detail & Related papers  (2021-02-07T19:51:02Z)
• Causal Feature Selection for Algorithmic Fairness [61.767399505764736]
  We consider fairness in the integration component of data management. We propose an approach to identify a sub-collection of features that ensure the fairness of the dataset.
  arXiv  Detail & Related papers  (2020-06-10T20:20:10Z)
• Hierarchical Feature Embedding for Attribute Recognition [26.79901907956084]
  We propose a hierarchical feature embedding framework, which learns a fine-grained feature embedding by combining attribute and ID information. Experiments show that our method achieves the state-of-the-art results on two pedestrian attribute datasets and a facial attribute dataset.
  arXiv  Detail & Related papers  (2020-05-23T17:52:41Z)

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.