Kwan Ho Ryan Chan's repositories
redunet_paper
Official NumPy Implementation of Deep Networks from the Principle of Rate Reduction (2021)
cifar100coarse
Build PyTorch CIFAR100 using coarse labels
style_transfer
Implementation of Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. 2016. “Image Style Transfer Using Convolutional Neural Networks.”
VariationalInformationPursuit
Official Implementation for Variational Information Pursuit for Interpretable Predictions (ICLR 2023)
vision-transformers-cifar10
Let's train vision transformers (ViT) for cifar 10!
barks
A simple, minimalistic theme for Hugo.
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
dgm23_GPT
A minimal and efficient Pytorch implementation of OpenAI's GPT (Generative Pretrained Transformer).
FT-CLIP
CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet
GraphVQA
GraphVQA: Language-Guided Graph Neural Networks for Scene Graph Question Answering
INVASE
Codebase for INVASE: Instance-wise Variable Selection - 2019 ICLR
ISONet
Deep Isometric Learning for Visual Recognition (ICML 2020)
ISTA-Net-PyTorch
ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing, CVPR2018 (PyTorch Code)
latent_ode
Code for "Latent ODEs for Irregularly-Sampled Time Series" paper
neuron-descriptions
Natural Language Descriptions of Deep Visual Features, ICLR 2022
pytorch-cifar
95.47% on CIFAR10 with PyTorch
ryanchankh.github.io
A beautiful, simple, clean, and responsive Jekyll theme for academics
ryanchankh.github.io_archive
Personal Website
SparseScatNet
Code implementation of paper: Deep Network Classification by Scattering and Homotopy Dictionary Learning
STAM-Sequential-Transformers-Attention-Model
Official implementation of "Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes" [CVPR'22]
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
ViLT
Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"