Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction

TL;DR

This paper proposes a novel two-stage noise correction strategy for pseudo-label guided learning in weakly-supervised temporal action localization, significantly improving detection accuracy and speed.

Contribution

It introduces a context-aware denoising algorithm and an online-revised teacher-student framework to address noise issues in pseudo-labels, enhancing localization performance.

Findings

Outperforms previous state-of-the-art on THUMOS14 and ActivityNet v1.2

Achieves higher detection accuracy and faster inference speed

Effectively handles boundary inaccuracies and short action clips

Abstract

Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the fully-supervised detection head. We argue that the noise in pseudo-labels would interfere with the learning of fully-supervised detection head, leading to significant performance leakage. Issues with noisy labels include:(1) inaccurate boundary localization; (2) undetected short action clips; (3) multiple adjacent segments incorrectly detected as one segment. To target these issues, we introduce a two-stage noisy label learning strategy to harness every potential useful signal in noisy labels. First, we propose a frame-level pseudo-label generation model with a context-aware denoising algorithm to refine the boundaries. Second, we introduce an online-revised teacher-student framework with a missing instance compensation module and an ambiguous instance correction module to solve the short-action-missing and many-to-one problems. Besides, we apply a high-quality pseudo-label mining loss in our online-revised teacher-student framework to add different weights to the noisy labels to train more effectively. Our model outperforms the previous state-of-the-art method in detection accuracy and inference speed greatly upon the THUMOS14 and ActivityNet v1.2 benchmarks.