Vision and AI Laboratory (VAL) -- IISc

lsc-cnn

sketch-parse

Code, demos and data for SketchParse (a neural network for sketch segmentation). Paper:

SDAT

[ICML 2022]Source code for "A Closer Look at Smoothness in Domain Adversarial Training",

NoisyTwins

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

Hard-Label-Model-Stealing

Saddle-LongTail

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

StickerDA

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

DeiT-LT

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

gSRGAN

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

NuAT

Towards Efficient and Effective Adversarial Training, NeurIPS 2021

DAJAT

Official Code for Efficient and Effective Augmentation Strategy for Adversarial Training (NeurIPS-2022)

s3vaada

Submodular Subset Selection for Active Domain Adaptation (ICCV 2021)

class-balancing-gan

Class Balancing GAN with a Classifier In The Loop (UAI 2021)

RMLVQA

DART

[CVPR-2023] Official Code for DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks

VL2V-ADiP

[CVPR 2024] Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification

MixupDA

[ICML22] Balancing Discriminability and Transferability for Source-Free Domain Adaptation

OAAT

Official Code for Scaling Adversarial Training to Large Perturbation Bounds (ECCV-2022)

CostSensitiveSelfTraining

[NeurIPS 2022] This repository contains the code for our work CSST: Cost Sensitive Self Training for Optimizing Non-Decomposable Objectives

FLSS

Official code for the paper - Boosting Adversarial Robustness using Feature Level Stochastic Smoothing

EffSSL

Towards Efficient and Effective Self-Supervised Learning of Visual Representations

SelMix

[ICLR 2024] [Spotlight]Code for our paper SelMix: Selective Mixup FineTuning

HSR

Code for Hierarchical Semantic Regularization of Latent Spaces in StyleGANs (ECCV 2022)

DSiT-SFDA

[ICCV23] Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation

C-SFTrans

ProFeAT

This codebase contains the implementation for the paper titled "ProFeAT: Projected Feature Adversarial Training for Self-Supervised Learning of Robust Representations".

assets

Geographical_Representativeness

NU-Certified-Robustness

[CVPRw 2023] Source Code for our Work "Certified Adversarial Robustness Within Multiple Perturbation Bounds"

val-iisc.github.io

Website for Video Analytics Lab, IISc Bangalore