BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation

Tianheng Cheng, Xinggang Wang, Shaoyu Chen, Qian Zhang, Wenyu Liu

Keywords: Weakly supervised instance segmentation, instance segmentation, object detection

TL;DR: This paper presents an end-to-end training framework named BoxTeacher to boost the performance of weakly supervised instance segmentation with high-quality pseudo labels.

Abstract: Labeling objects with pixel-wise segmentation requires a huge amount of human labor compared to bounding boxes. Most existing methods for weakly supervised instance segmentation focus on designing heuristic losses with priors from bounding boxes. While we find that box-supervised methods can produce some fine segmentation masks and we wonder whether the detectors could learn from these fine masks while ignoring low-quality masks. To answer this question, we present BoxTeacher, an efficient and end-to-end training framework for high-performance weakly supervised instance segmentation, which leverages a sophisticated teacher to generate high-quality masks as pseudo labels. Considering the massive noisy masks hurt the training, we present a mask-aware confidence score to estimate the quality of pseudo masks and propose the noise-aware pixel loss and noise-reduced affinity loss to adaptively optimize the student with pseudo masks. Extensive experiments can demonstrate the effectiveness of the proposed BoxTeacher. Without bells and whistles, BoxTeacher remarkably achieves $34.4$ mask AP and $35.4$ mask AP with ResNet-50 and ResNet-101 respectively on the challenging MS-COCO dataset, which outperforms the previous state-of-the-art methods by a significant margin. The code and models will be available later.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/boxteacher-exploring-high-quality-pseudo/code)