REVIEW 2 cited by
Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 2 Pith papers
-
ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices
Trainable commuting angle matrices generalize Rotary Position Embedding and improve accuracy and resolution robustness on vision Transformers.
-
IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt Learning
IMDPrompter learns cross-view prompts for SAM from RGB, SRM, Bayer, and Noiseprint features, and reports state-of-the-art image manipulation detection and localization on five benchmarks.
Discussion (0). Continue with ORCID to comment.