Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification

TY - GEN

T1 - Where to Focus

T2 - Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification

AU - Liu, Yang

AU - Zhou, Lei

AU - Zhang, Pencheng

AU - Xiao, Bai

AU - Gu, Lin

AU - Yu, Xiaohan

AU - Zhou, Jun

AU - Hancock, Edwin R

N1 - This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

PY - 2022/11/6

Y1 - 2022/11/6

N2 - Object categories are often grouped into a multi-granularity taxonomic hierarchy. Classifying objects at coarser-grained hierarchy requires global and common characteristics, while finer-grained hierarchy classification relies on local and discriminative features. Therefore, humans should also subconsciously focus on different object regions when classifying different hierarchies. This granularity-wise attention is confirmed by our collected human real-time gaze data on different hierarchy classifications. To leverage this mechanism, we propose a Cross-Hierarchical Region Feature (CHRF) learning framework. Specifically, we first design a region feature mining module that imitates humans to learn different granularity-wise attention regions with multi-grained classification tasks. To explore how human attention shifts from one hierarchy to another, we further present a cross-hierarchical orthogonal fusion module to enhance the region feature representation by blending the original feature and an orthogonal component extracted from adjacent hierarchies. Experiments on five hierarchical fine-grained datasets demonstrate the effectiveness of CHRF compared with the state-of-the-art methods. Ablation study and visualization results also consistently verify the advantages of our human attention-oriented modules. The code and dataset are available at https://github.com/visiondom/CHRF.

AB - Object categories are often grouped into a multi-granularity taxonomic hierarchy. Classifying objects at coarser-grained hierarchy requires global and common characteristics, while finer-grained hierarchy classification relies on local and discriminative features. Therefore, humans should also subconsciously focus on different object regions when classifying different hierarchies. This granularity-wise attention is confirmed by our collected human real-time gaze data on different hierarchy classifications. To leverage this mechanism, we propose a Cross-Hierarchical Region Feature (CHRF) learning framework. Specifically, we first design a region feature mining module that imitates humans to learn different granularity-wise attention regions with multi-grained classification tasks. To explore how human attention shifts from one hierarchy to another, we further present a cross-hierarchical orthogonal fusion module to enhance the region feature representation by blending the original feature and an orthogonal component extracted from adjacent hierarchies. Experiments on five hierarchical fine-grained datasets demonstrate the effectiveness of CHRF compared with the state-of-the-art methods. Ablation study and visualization results also consistently verify the advantages of our human attention-oriented modules. The code and dataset are available at https://github.com/visiondom/CHRF.

U2 - 10.1007/978-3-031-20053-3_4

DO - 10.1007/978-3-031-20053-3_4

M3 - Conference contribution

SN - 9783031200533

T3 - Lecture Notes in Computer Science (LNCS)

SP - 57

EP - 73

BT - Proceedings ECCV 2022

A2 - Avidan, Shai

A2 - Brostow, Gabriel

A2 - Cissé, Moustapha

A2 - Farinella, Giovanni Maria

A2 - Hassner, Tal

PB - Springer

CY - Cham

ER -