When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling

arXiv:2609.33668 · cs.CV, cs.AI · Submitted 2026-09-27 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-27

Updated: 2026-09-27

Comments: Accepted to NeurIPS 2026 Main Track. Code: https://github.com/pingggg516/FTC-Seg

Code: https://github.com/pingggg516/FTC-Seg

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 14× in this paper · explained in 7 episodes
• Pseudo-labeling — 14× in this paper · explained in 3 episodes
• Benchmark — 11× in this paper · explained in 2 episodes
• Consistency — 10× in this paper · explained in 3 episodes
• Pseudo-labels — 8× in this paper · explained in 2 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• Adaptive Threshold Calibration — 6× in this paper
• Entanglement — 6× in this paper · explained in 4 episodes
• Orthogonal Prototype Reconstruction — 6× in this paper
• Semi-supervised Learning — 6× in this paper · explained in 4 episodes
• Aggregation — 3× in this paper
• Regularization — 3× in this paper · explained in 3 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Decoupling — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Exponential Moving Average (EMA) — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• CTFS: Collaborative Teacher Framework for Forward-Looking Sonar Image Semantic Segmentation with Extremely Limited Labels
• Decoupled Weight Decay Regularization
• DINOv2: Learning Robust Visual Features without Supervision
• Pseudo-Label Noise Suppression Techniques for Semi-Supervised Semantic Segmentation
• FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models