Distraction-Aware Feature Learning for Human Attribute Recognition via Coarse-to-Fine Attention Mechanism
This addresses the challenge of attribute localization in HAR, which is crucial for applications like surveillance and biometrics, but it appears incremental as it builds on existing attention mechanisms.
The paper tackles the problem of localizing attributes in Human Attribute Recognition (HAR) by proposing a distraction-aware deep learning approach with a coarse-to-fine attention mechanism, achieving state-of-the-art results on WIDER-Attribute and RAP databases.
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.