Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

CW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation

AI By Crimson AI Hugging Face Papers 15 August 2026 · 00:00 13 views
Share: X Telegram

A new method, CW-BASS v2, adapts pseudo-label selection to the saturated confidence of foundation-model teachers, improving semi-supervised segmentation across benchmarks.

CW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation

Key points

Semi-supervised semantic segmentation has long relied on pseudo-label selection rules—dynamic thresholds, per-class curricula, and soft confidence weights—designed for noisy, under-confident ResNet teachers. However, self-supervised foundation encoders like DINOv2 change the regime: confidence saturates, with 98% of Pascal VOC pixels at or above 0.95 confidence. This saturation can cause adaptive cutoffs to flood the retention mask, degrading self-training into confirmation bias.

CW-BASS v2, introduced in a new paper, addresses this by measuring the teacher's confidence regime rather than assuming one. It uses a one-pass reliability gate that estimates pi_kept = Pr[correct | c >= tau] on a held-out slice. If the confident set is as reliable as the demanded confidence (pi_kept >= tau), it filters strictly; otherwise, it falls back to a self-adaptive floor. The boundary is the pre-existing operating threshold, not tuned to mIoU.

Across six DINOv2 teachers, CW-BASS v2 makes the correct strict-vs-floor call blindly. It recovers the UniMatch V2 operating point on saturated benchmarks: Pascal VOC 1/8 achieves 87.4 mIoU (vs. 87.9 reported), and Cityscapes is within 0.5. On ADE20K, where the confident set is unreliable (pi_kept ~89% vs. 98%), the adaptive floor edges ahead by +1.5 mIoU (single seed).

The method's principle is that the failure it avoids is measured, not assumed. Code, weights for Pascal/Cityscapes/ADE20K, and a Gradio demo are available in the repository.

BenchmarkCW-BASS v2 (mIoU)UniMatch V2 reported (mIoU)
Pascal VOC 1/887.487.9
Cityscapeswithin 0.5-
ADE20K (pi_kept ~89%)+1.5 (single seed)-
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 29 Aug 2026

Hugging Face Audit: 110 of 124 AI Evaluations Fail to Support Their Claims

A new commit-bound census of 124 Inspect Evals units reveals that 110 stop before deterministic inference due to missing historica...

4
Research paper
Hugging Face 29 Aug 2026

Aphanta: New Framework Diagnoses When Image Editing Boosts Multimodal Reasoning

Hugging Face researchers introduce Aphanta, a diagnostic framework that evaluates when image-editing intermediates improve multimo...

5
Research paper
Hugging Face 29 Aug 2026

EditaLive! Enables Real-Time Character Video Editing for Live Streaming

Hugging Face researchers introduce EditaLive, a framework for real-time human-centric video editing in live streams, achieving sta...

4