Vision and AI Laboratory (VAL) -- IISc

Code repository for the paper: Appearance Consensus Driven Self-Supervised Human Mesh Recovery

val-iisc

[ECCV22] Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation

val-iisc

[ECCV2022] Source Code for "Improving GANs for Long-Tailed Data through Group Spectral Regularization"

val-iisc

val-iisc

[CVPR 2023] Source code for NoisyTwins: Class-consistent and Diverse Image Generation Through StyleGANs

val-iisc

Towards Efficient and Effective Adversarial Training, NeurIPS 2021

val-iisc

[NeurIPS 2022] Source code for our paper "Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data"

val-iisc

Universal Source-Free Domain Adaptation (CVPR 2020)

val-iisc

[CVPR 2024] Code for our Paper "DeiT-LT: Distillation Strikes Back for Vision Transformer training on Long-Tailed Datasets"

val-iisc