MultiTask Learning of Object Detection and Semantic Segmentation

Abstract

Self-training allows a network to learn from the predictions of a more complicated model, thus often requires well-trained teacher models and mixture of teacher-student data while multi-task learning jointly optimizes different targets to learn salient interrelationship and requires multi-task annotations for each training example. These frameworks, despite being particularly data demanding have potentials for data exploitation if such assumptions can be relaxed. In this paper, we compare self-training object detection under the deficiency of teacher training data where students are trained on unseen examples by the teacher, and multi-task learning with partially annotated data, i.e. single-task annotation per training example. Both scenarios have their own limitation but potentially helpful with limited annotated data. Experimental results show the improvement of performance when using a weak teacher with unseen data for training a multi-task student. Despite the limited setup we believe the experimental results show the potential of multi-task knowledge distillation and self-training, which could be beneficial for future study.

Source code and data splits are at Github

Paper

arxiv

Citation

If you find the material useful please consider citing our work

@inproceedings{le23iccvw,
 author = {L{\^{e}}, Ho{\`{a}}ng{-}{\^{A}}n and and Pham, Minh-Tan},
 title = {{Self-Training and Multi-task Learning for Limited Data: Evaluation
 Study on Object Detection}},
 booktitle = {Proceedings of the IEEE/CVF International Conference of Computer Vision (ICCV) workshop},
 year = {2023},
}