Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition

TL;DR

This paper introduces a Spatial and Semantic Consistency (SSC) framework for pedestrian attribute recognition that leverages inter-image relations and human priors to improve accuracy without increasing model complexity.

Contribution

The paper proposes a novel SSC framework with regularizations for spatial and semantic consistency, enhancing attribute recognition by exploiting inter-image relations and prior knowledge.

Findings

Outperforms state-of-the-art methods on PA100K, RAP, and PETA datasets.

Improves attribute localization and semantic feature extraction.

Achieves better accuracy without increasing model parameters.

Abstract

While recent studies on pedestrian attribute recognition have shown remarkable progress in leveraging complicated networks and attention mechanisms, most of them neglect the inter-image relations and an important prior: spatial consistency and semantic consistency of attributes under surveillance scenarios. The spatial locations of the same attribute should be consistent between different pedestrian images, \eg, the ``hat" attribute and the ``boots" attribute are always located at the top and bottom of the picture respectively. In addition, the inherent semantic feature of the ``hat" attribute should be consistent, whether it is a baseball cap, beret, or helmet. To fully exploit inter-image relations and aggregate human prior in the model learning process, we construct a Spatial and Semantic Consistency (SSC) framework that consists of two complementary regularizations to achieve spatial and semantic consistency for each attribute. Specifically, we first propose a spatial consistency regularization to focus on reliable and stable attribute-related regions. Based on the precise attribute locations, we further propose a semantic consistency regularization to extract intrinsic and discriminative semantic features. We conduct extensive experiments on popular benchmarks including PA100K, RAP, and PETA. Results show that the proposed method performs favorably against state-of-the-art methods without increasing parameters.