LangTail uses entity-level semantic priors from language models aligned via contrastive learning in a hierarchical clustering setup to resolve long-tail ambiguity, yielding +13.5, +12.9, and +8.9 mIoU gains on ScanNet-v2, S3DIS, and nuScenes.
arXiv preprint arXiv:2203.08414 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Boxes2Pixels distills noisy SAM pseudo-masks into a compact DINOv2-based student with auxiliary localization and one-sided self-correction, delivering +6.97 anomaly mIoU and +9.71 binary IoU gains over baselines on wind turbine data with 80% fewer parameters.
Register tokens enhance pixel-space DiT training and output quality via cleaner high-noise feature maps, and a dual-stream design adds further gains with little overhead.
SSL clustering is derived as KL-divergence optimization where a teacher-distribution constraint normalizes via inverse cluster priors and simplifies to batch centering by Jensen's inequality.
An unsupervised monocular road segmentation method generates initial labels from horizon and quadrilateral geometric priors then refines them via temporal feature tracking and mutual information to reach 0.86 IoU on Cityscapes.
citing papers explorer
-
Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors
LangTail uses entity-level semantic priors from language models aligned via contrastive learning in a hierarchical clustering setup to resolve long-tail ambiguity, yielding +13.5, +12.9, and +8.9 mIoU gains on ScanNet-v2, S3DIS, and nuScenes.
-
Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks
Boxes2Pixels distills noisy SAM pseudo-masks into a compact DINOv2-based student with auxiliary localization and one-sided self-correction, delivering +6.97 anomaly mIoU and +9.71 binary IoU gains over baselines on wind turbine data with 80% fewer parameters.
-
Registers Matter for Pixel-Space Diffusion Transformers
Register tokens enhance pixel-space DiT training and output quality via cleaner high-noise feature maps, and a dual-stream design adds further gains with little overhead.
-
Information theoretic underpinning of self-supervised learning by clustering
SSL clustering is derived as KL-divergence optimization where a teacher-distribution constraint normalizes via inverse cluster priors and simplifies to batch centering by Jensen's inequality.
-
Unsupervised Monocular Road Segmentation for Autonomous Driving via Scene Geometry
An unsupervised monocular road segmentation method generates initial labels from horizon and quadrilateral geometric priors then refines them via temporal feature tracking and mutual information to reach 0.86 IoU on Cityscapes.