pseudo-labels

[ICLR-2020] Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification.

Uncertainty-aware Fine-tuning of Segmentation Foundation Models (NeurIPS 2024).

Python library for automatic CV dataset labeling - classification, detection, segmentation, VQA, OCR, feature matching with SOTA models.

This is the repository of paper Blind Image Quality Assessment by Learning and Adapting from Multiple Annotators

Zero-manual-annotation multi-view 3D label-production pipeline for high-occlusion contact sports, plus the monocular lifting recipe built on it — with a layer-wise error budget of what each stage costs

Commissioned WSSS research with frozen CLIP and DINOv2, disagreement-aware pseudo-mask refinement, and 53.31% mIoU on COCO-Val.