FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding
Truong, Thanh Dat Prabhu, Utsav Raj, Bhiksha Cothren, Jackson D. Luu, Khoa
Truong, Thanh Dat
Prabhu, Utsav
Raj, Bhiksha
Cothren, Jackson D.
Luu, Khoa
Author
Supervisor
Department
Natural Language Processing
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Continual Learning in semantic scene segmentation aims to continually learn new unseen classes in dynamic environments while maintaining previously learned knowledge. Prior studies focused on modeling the catastrophic forgetting and background shift challenges in continual learning. However, fairness, another major challenge that causes unfair predictions leading to low performance among major and minor classes, still needs to be well addressed. In addition, prior methods have yet to model the unknown classes well, thus resulting in producing non-discriminative features among unknown classes. This work presents a novel Fairness Learning via Contrastive Attention Approach to continual learning in semantic scene understanding. In particular, we first introduce a new Fairness Contrastive Clustering loss to address the problems of catastrophic forgetting and fairness. Then, we propose an attention-based visual grammar approach to effectively model the background shift problem and unknown classes, producing better feature representations for different unknown classes. Through our experiments, our proposed approach achieves State-of-the-Art (SoTA) performance on different continual learning benchmarks, i.e., ADE20K, Cityscapes, and Pascal VOC. It promotes the fairness of the continual semantic segmentation model.
Citation
T. -D. Truong, U. Prabhu, B. Raj, J. Cothren and K. Luu, "FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding," 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2025, pp. 15065-15075, doi: 10.1109/CVPR52734.2025.01403.
Source
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Conference
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025
Keywords
Continual Learning, Contrastive Attention Learning, Semantic Segmentation
Subjects
Source
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025
Publisher
IEEE