Incremental Learning in Semantic Segmentation from Image Labels

By Fabio Cermelli, Dario Fontanel, A. Tavera, Marco Ciccone, Barbara Caputo. 2021

69 citations recorded by the source corpus.

Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and time-consuming. This paper proposes a novel framework for Weakly Incremental Learning for Semantic Segmentation, that aims at learning to segment new classes from cheap and largely available image-level labels. As opposed to existing approaches, that need to generate pseudolabels offline, we use a localizer, trained with image-level labels and regularized by the segmentation model, to obtain pseudo-supervision online and update the model incrementally. We cope with the inherent noise in the process by using soft-labels generated by the localizer. We demonstrate the effectiveness of our approach on the Pascal VOC and COCO datasets, outperforming offline weakly-supervised methods and obtaining results comparable with incremental learning methods with full supervision.11Code can be found at https://github.com/fcd194/WILSON.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Meta & Continual Learning

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. Han-Jia Ye
2. De-chuan Zhan
3. Da-Wei Zhou
4. Hang Su
5. Qiwen Wang
6. Jun Zhu
7. Ziwei Liu
8. Liyuan Wang

In Computer Vision and Pattern Recognition

1. Han-Jia Ye
2. De-chuan Zhan
3. Jun Zhu
4. Da-Wei Zhou
5. Hang Su
6. Ziwei Liu
7. Liyuan Wang
8. Joost van de Weijer

In Meta & Continual Learning

1. Han-Jia Ye
2. De-chuan Zhan
3. Da-Wei Zhou
4. Xingxing Zhang
5. Liyuan Wang
6. Hang Su
7. Jun Zhu
8. Qiwen Wang

Citations in the corpus

• A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, methodology): “PLOP [292], RECALL [293], SSUL [294], Self-Training [295] and WILSON [296] explicitly apply the old model to generate pseudo-labels of the old classes.”
• Towards Label-Efficient Incremental Learning: A Survey (2023, background): “We note that the initial effort(s) have been made for weakly-supervised incremental object segmentation, however with limited performance over non-incremental counterparts [ Cermelli et al. , 2022 ] .”
• Deep Class-Incremental Learning: A Survey (2023, background): “, semantic segmentation [164], [165], [166], [167], [174], object detection [175], [176], [177], [178], [179], [180], [181], video understanding [95], [133], medical surgery [182], [183], language model [184], [185], [186], [187], language-vision model [188], [189], etc.”
• Continual Segmentation with Disentangled Objectness Learning and Class Recognition (2024, unknown): “Some works [4, 20] started to focus on more realistic scenarios by integrating weak super-vision [56, 62] with continual learning.”
• Class-Incremental Learning: A Survey (2023, methodology): “Furthermore, it has shown the potential to apply the techniques in classification into other tasks, e.g. , semantic segmentation [193], [238], [239], [240], [241], object detection [137], [242], [243], [244], [245], [246], [247], video understanding [91], [161], medical surgery [248], [249],…”