# Distraction-Aware Feature Learning for Human Attribute Recognition via Coarse-to-Fine Attention Mechanism

arXiv: https://arxiv.org/abs/1911.11351 · HTML: https://mlsanity.com/paper/1911.11351/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2019.

## Built on by (most cited first, 11 of 11)

- [Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting](https://mlsanity.com/paper/2107.03576/) (2021)
- [Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion](https://mlsanity.com/paper/2312.10692/) (2023)
- [An Empirical Study of Mamba-based Pedestrian Attribute Recognition](https://mlsanity.com/paper/2407.10374/) (2024)
- [Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework](https://mlsanity.com/paper/2408.09720/) (2024)
- [Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization](https://mlsanity.com/paper/2106.06485/) (2021)
- [SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition](https://mlsanity.com/paper/2312.06049/) (2023)
- [RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Framework](https://mlsanity.com/paper/2504.10018/) (2025)
- [Reinforced Pedestrian Attribute Recognition with Group Optimization Reward](https://mlsanity.com/paper/2205.14042/) (2022)
- [Portrait Interpretation and a Benchmark](https://mlsanity.com/paper/2207.13315/) (2022)
- [WaveNets: Wavelet Channel Attention Networks](https://mlsanity.com/paper/2211.02695/) (2022)
- [Native Association: Confidence-Aware Human Perception in the Wild with a Foundation VLM](https://mlsanity.com/paper/2609.33450/) (2026)

## Abstract (arXiv)

Recently, Human Attribute Recognition (HAR) has become a hot topic due to its scientific challenges and application potentials, where localizing attributes is a crucial stage but not well handled. In this paper, we propose a novel deep learning approach to HAR, namely Distraction-aware HAR (Da-HAR). It enhances deep CNN feature learning by improving attribute localization through a coarse-to-fine attention mechanism. At the coarse step, a self-mask block is built to roughly discriminate and reduce distractions, while at the fine step, a masked attention branch is applied to further eliminate irrelevant regions. Thanks to this mechanism, feature learning is more accurate, especially when heavy occlusions and complex backgrounds exist. Extensive experiments are conducted on the WIDER-Attribute and RAP databases, and state-of-the-art results are achieved, demonstrating the effectiveness of the proposed approach.