Seminar Learning for Click-Level Weakly Supervised Semantic Segmentation

TL;DR

This paper introduces seminar learning, a novel paradigm for click-level weakly supervised semantic segmentation that leverages multiple networks to improve performance, achieving state-of-the-art results on Pascal VOC 2012.

Contribution

It proposes seminar learning, combining teacher-student and student-student modules, to enhance weak supervision in semantic segmentation with click-level annotations.

Findings

Achieves 72.51% mIOU on Pascal VOC 2012

Surpasses previous methods by up to 16.88%

Demonstrates effectiveness of knowledge transfer among networks

Abstract

Annotation burden has become one of the biggest barriers to semantic segmentation. Approaches based on click-level annotations have therefore attracted increasing attention due to their superior trade-off between supervision and annotation cost. In this paper, we propose seminar learning, a new learning paradigm for semantic segmentation with click-level supervision. The fundamental rationale of seminar learning is to leverage the knowledge from different networks to compensate for insufficient information provided in click-level annotations. Mimicking a seminar, our seminar learning involves a teacher-student and a student-student module, where a student can learn from both skillful teachers and other students. The teacher-student module uses a teacher network based on the exponential moving average to guide the training of the student network. In the student-student module, heterogeneous pseudo-labels are proposed to bridge the transfer of knowledge among students to enhance each other's performance. Experimental results demonstrate the effectiveness of seminar learning, which achieves the new state-of-the-art performance of 72.51% (mIOU), surpassing previous methods by a large margin of up to 16.88% on the Pascal VOC 2012 dataset.