Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation

By Minh-Hieu Phan, The-Anh Ta, Son Lam Phung, Long Tran-Thanh, Abdesselam Bouzerdoum. 2022

83 citations recorded by the source corpus.

Deep learning models are known to suffer from the problem of catastrophic forgetting when they incrementally learn new classes. Continual learning for semantic segmentation (CSS) is an emerging field in computer vision. We identify a problem in CSS: A model tends to be confused between old and new classes that are visually similar, which makes it forget the old ones. To address this gap, we propose REMINDER - a new CSS framework and a novel class similarity knowledge distillation (CSW-KD) method. Our CSW-KD method distills the knowledge of a previous model on old classes that are similar to the new one. This provides two main benefits: (i) selectively revising old classes that are more likely to be forgotten, and (ii) better learning new classes by relating them with the previously seen classes. Extensive experiments on Pascal-Voc 2012 and ADE20k datasets show that our approach outperforms state-of-the-art methods on standard CSS settings by up to 7.07% and 8.49%, respectively.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Beomyoung Kim
2. Sung Ju Hwang
3. Huisi Wu
4. Jing Qin
5. Joonsang Yu
6. Huyong Wang

In Computer Vision and Pattern Recognition

1. Beomyoung Kim
2. Sung Ju Hwang
3. Huisi Wu
4. Jing Qin
5. Joonsang Yu
6. Huyong Wang

Citations in the corpus

• ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning (2024, methodology): “Recently, various continual segmentation methods [2, 5, 11, 35, 37, 40, 46, 47, 49] have emerged, addressing the key challenges and showing notable improvements.”
• Incremental Nuclei Segmentation from Histopathological Images via Future-class Awareness and Compatibility-inspired Distillation (2024, background): “Except for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore. in clinical scenarios, most studies turn to employ distillation techniques [4, 13, 23, 25, 26, 30, 36] to constrain the model updating.”
• Continual Segmentation with Disentangled Objectness Learning and Class Recognition (2024, unknown): “Following standard continual segmentation base-lines [3, 12, 36], we evaluate semantic segmentation performance of CoMasTRe on PASCAL VOC 2012 [14] and ADE20K [63].”