Uncertainty-Aware Contrastive Distillation for Incremental Semantic Segmentation

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 2; pp. 2567 - 2581
• Main Authors: Yang, Guanglei, Fini, Enrico, Xu, Dan, Rota, Paolo, Ding, Mingli, Nabi, Moin, Alameda-Pineda, Xavier, Ricci, Elisa
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Catastrophic failure analysis; Computer Science; Computer vision; Computer Vision and Pattern Recognition; contrastive learning; Deep learning; Distillation; Feature extraction; Image classification; Image segmentation; incremental learning; Knowledge acquisition; Knowledge distillation; Machine Learning; Neural networks; Object recognition; Pixels; Semantic segmentation; Semantics; Task analysis; Training; Uncertainty
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2022.3163806

A fundamental and challenging problem in deep learning is catastrophic forgetting, i.e., the tendency of neural networks to fail to preserve the knowledge acquired from old tasks when learning new tasks. This problem has been widely investigated in the research community and several Incremental Learning (IL) approaches have been proposed in the past years. While earlier works in computer vision have mostly focused on image classification and object detection, more recently some IL approaches for semantic segmentation have been introduced. These previous works showed that, despite its simplicity, knowledge distillation can be effectively employed to alleviate catastrophic forgetting. In this paper, we follow this research direction and, inspired by recent literature on contrastive learning, we propose a novel distillation framework, Uncertainty-aware Contrastive Distillation (UCD). In a nutshell, UCDis operated by introducing a novel distillation loss that takes into account all the images in a mini-batch, enforcing similarity between features associated to all the pixels from the same classes, and pulling apart those corresponding to pixels from different classes. In order to mitigate catastrophic forgetting, we contrast features of the new model with features extracted by a frozen model learned at the previous incremental step. Our experimental results demonstrate the advantage of the proposed distillation technique, which can be used in synergy with previous IL approaches, and leads to state-of-art performance on three commonly adopted benchmarks for incremental semantic segmentation.