Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning


Hoàng-Ân Lê (Université de Bretagne Sud), Paul Berg (Université de Bretagne Sud), Minh Tan Pham (Université de Bretagne Sud)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Object detection and semantic segmentation are both scene understanding tasks yet they differ in data structure and information level. Object detection requires box-coordinates for object instances while semantic segmentation pixel-wise class labels. Making use of one task’s information to train the other would be beneficial for multi-task partially supervised learning where each training example is annotated only for a single task, having the potential to expand training sets with different-task datasets. In this paper, various weak losses are studied for partially annotated data in combination with existing supervised losses. We propose Box-for-Mask and Mask-for-Box strategies, and their combination BoMBo, to distil necessary information from one task annotations to train the other. Ablation studies and experimental results on both VOC and COCO datasets show favorable results for the proposed idea. Source code and data splits will be released upon acceptance.

Citation

@inproceedings{Lê_2024_BMVC,
author    = {Hoàng-Ân Lê and Paul Berg and Minh Tan Pham},
title     = {Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning},
booktitle = {35th British Machine Vision Conference 2024, {BMVC} 2024, Glasgow, UK, November 25-28, 2024},
publisher = {BMVA},
year      = {2024},
url       = {https://papers.bmvc2024.org/0753.pdf}
}


Copyright © 2024 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection