code released for our ICML 2020 paper "Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation"

PyTorch open-source toolbox for unsupervised or domain adaptive object re-ID.

Winning solution for the Kaggle TGS Salt Identification Challenge.

TGS Salt Identification

A full pipeline AutoML tool for tabular data

Labelling platform for text using weak supervision.

"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning" by Mamshad Nayeem Rizve, Kevin Duarte, Yogesh S Rawat, Mubarak Shah (ICLR 2021)

[NAACL 2021] This is the code for our paper `Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach'.

Experiments on Flood Segmentation on Sentinel-1 SAR Imagery with Cyclical Pseudo Labeling and Noisy Student Training

PromptDet: Towards Open-vocabulary Detection using Uncurated Images, ECCV2022

[IJCAI 2022] Official Pytorch code for paper “S2 Transformer for Image Captioning”

Weakly supervised medical named entity classification

Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling

[NeurIPS 2022] Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering

Semi-Supervised Hyperspectral Image Classification

[IJCAI 2023] Co-training with High-Confidence Pseudo Labels for Semi-supervised Medical Image Segmentation

"Towards Realistic Semi-Supervised Learning" by Mamshad Nayeem Rizve, Navid Kardan, Mubarak Shah (ECCV 2022)

"OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning" by Mamshad Nayeem Rizve, Navid Kardan, Salman Khan, Fahad Shahbaz Khan, Mubarak Shah (ECCV 2022)

The dataset for the paper 'Learning self-supervised traversability with navigation experiences of mobile robots: A risk-aware self-training approach'

[ECCV2024] Mitigating Background Shift in Class-Incremental Semantic Segmentation