Abstract
Co-salient object detection (CoSOD) together with the rapid development of deep learning has led to substantial progress in recent years. However, the feature aggregation between group feature representation and individual feature representation is still a challenging issue. In this work, we propose a novel adaptive intra-group aggregation (AIGA) method, which provides a new perspective to investigate the interaction relationship between group and single-image features and aggregate these features in an adaptive way. A novel scale-aware loss is proposed to help the model capture the scale prior of different groups and discriminatively process groups during the training phase. Extensive experiments demonstrate that the proposed method can effectively improve the performance without increasing extra parameters and achieve better accuracy on three prevalent benchmarks.
Original language | English |
---|---|
Title of host publication | IEEE International Conference on Acoustics, Speech and Signal Processing |
Publisher | IEEE Explore |
Pages | 2520-2524 |
Number of pages | 5 |
ISBN (Electronic) | 978-1-6654-0540-9 |
DOIs | |
Publication status | Published - 27 Apr 2022 |
Externally published | Yes |
Event | 2022 IEEE International Conference on Acoustics, Speech and Signal Processing - , Singapore Duration: 22 May 2022 → 27 May 2022 https://2022.ieeeicassp.org/ |
Publication series
Name | IEEE International Conference on Acoustics, Speech and Signal Processing |
---|---|
Publisher | IEEE |
ISSN (Electronic) | 2379-190X |
Seminar
Seminar | 2022 IEEE International Conference on Acoustics, Speech and Signal Processing |
---|---|
Abbreviated title | ICASSP 2022 |
Country/Territory | Singapore |
Period | 22/05/22 → 27/05/22 |
Internet address |
Keywords
- co-salient object detection
- determinantal point processes