Uncertainty estimation and regularization on weak positive pairs improves mAP by 3.06%, 3.55%, and 6.94% on CUHK-PEDES, RSTPReid, and ICFG-PEDES respectively.
Modeling uncer- tainty with hedged instance embedding
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3roles
background 1polarities
background 1representative citing papers
PVeRA extends VeRA by making its frozen random low-rank matrices probabilistic, enabling better handling of ambiguities and outperforming prior adapters on the VTAB-1k benchmark.
Training tweaks (augmentations, hybrid loss, scheduling, ablation flags) raise optic disc Dice from 0.939 (baseline epoch 5) to 0.956 (final epoch) on a fundus benchmark.
citing papers explorer
-
Harnessing Weak Pair Uncertainty for Text-based Person Search
Uncertainty estimation and regularization on weak positive pairs improves mAP by 3.06%, 3.55%, and 6.94% on CUHK-PEDES, RSTPReid, and ICFG-PEDES respectively.
-
PVeRA: Probabilistic Vector-Based Random Matrix Adaptation
PVeRA extends VeRA by making its frozen random low-rank matrices probabilistic, enabling better handling of ambiguities and outperforming prior adapters on the VTAB-1k benchmark.
-
ROBUST-WT: Robust Uncertainty-aware Segmentation Transform via Whitening and Training Enhancements
Training tweaks (augmentations, hybrid loss, scheduling, ablation flags) raise optic disc Dice from 0.939 (baseline epoch 5) to 0.956 (final epoch) on a fundus benchmark.