Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023

📟 Links to others' solutions to Projects (https://github.com/karan/Projects/)

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Benchmarks for Out-of-Distribution Generalization in Time Series Tasks

CVPR2022: Meta-attention for ViT-backed Continual Learning

Learning to Prompt (L2P) for Continual Learning @ CVPR22

The official PyTorch code for ICLR'22 Paper "Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System""

[ICLR 22] Latent Image Animator: Learning to Animate Images via Latent Space Navigation

An All-MLP solution for Vision, from Google AI

Fit interpretable models. Explain blackbox machine learning.

ACDC: Online Unsupervised Cross-Domain Adaptation

Code for "The Intrinsic Dimension of Images and Its Impact on Learning" - ICLR 2021 Spotlight https://openreview.net/forum?id=XJk19XzGq2J

GAN, transfer learning, few data.

( NeurIPS 2020 ) Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation

Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM

[Preprint] "TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up", Yifan Jiang, Shiyu Chang, Zhangyang Wang

[CVPR '21] Official repository for Few-shot Image Generation via Cross-domain Correspondence

Implementation of Segformer, Attention + MLP neural network for segmentation, in Pytorch

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

Deep Survival Machines - Fully Parametric Survival Regression

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Pengfei Huang,Handing Wang,Yaochu Jin,Offine Data-Driven Evolutionary Optimization Based on Tri-Training, Swarm and Evolutionary Computation, Accepted.

This repository contains the codes to reproduce the results of our proposed novelty detection algorithm based on adversarially robust autoencoder.