Awesome Few-Shot Class-Incremental Learning

Best Practices on Recommendation Systems

Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai

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

PyTorch implementation of AutoAugment.

Implementation of "Transductive Zero-Shot Learning for 3D Point Cloud Classification"

Official codebase for the ECCV 2022 paper Transfer without Forgetting

CVPR2022: Meta-attention for ViT-backed Continual Learning

Codes and data for the paper: M. Alfarraj, and G. AlRegib, "Semi-Supervised Sequence Modeling for Elastic Impedance Inversion," in Interpretation, Aug. 2019

Official implementation for "Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images" https://arxiv.org/abs/2112.08810

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)

Images of the PerxonX dataset and the original 3D human models of this dataset

An All-MLP solution for Vision, from Google AI

Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two

Learning to Prompt (L2P) for Continual Learning @ CVPR22 and DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning @ ECCV22

[ICLR 22, TPAMI 24] Latent Image Animator

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

Contains code for the NeurIPS 2019 paper "Practical Deep Learning with Bayesian Principles"

(ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"

An alternative to convolution in neural networks

Code to reproduce experiments from 'Does Knowledge Distillation Really Work' a paper which appeared in the 2021 NeurIPS proceedings.

Code for visualizing the loss landscape of neural nets

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Pytorch implementation of common image generation metrics.