ushuaia009's starred repositories
suncet
Code to reproduce the results in the FAIR research papers "Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples" https://arxiv.org/abs/2104.13963 and "Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations" https://arxiv.org/abs/2006.10803
dti-sprites
(ICCV 2021) Code for "Unsupervised Layered Image Decomposition into Object Prototypes" paper
mlp-mixer-pytorch
An All-MLP solution for Vision, from Google AI
PoseContrast
(3DV 2021 oral) PyTorch implementation of paper "PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning"
Patch-NetVLAD
Code for the CVPR2021 paper "Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition"
ImageNet-Sketch
ImageNet-Sketch data set for evaluating model's ability in learning (out-of-domain) semantics at ImageNet scale
self-label
Self-labelling via simultaneous clustering and representation learning. (ICLR 2020)
wavelet-monodepth
[CVPR 2021] Monocular depth estimation using wavelets for efficiency
3D-Machine-Learning
A resource repository for 3D machine learning
wild_deep_mvs
Code release of paper "Deep Multi-View Stereo gone wild"
Localizing-Visual-Sounds-the-Hard-Way
Localizing Visual Sounds the Hard Way
zrqiao.github.io
A beautiful, simple, clean, and responsive Jekyll theme for academics
project-webpage
Simple template for a project webpage
VQGAN-CLIP
Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
awesome-self-supervised-learning
A curated list of awesome self-supervised methods
single_img_pretraining
Code for generating a single image pretraining dataset
GANSketching
Sketch Your Own GAN: Customizing a GAN model with hand-drawn sketches.
frozen-in-time
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [ICCV'21]
deepmind-research
This repository contains implementations and illustrative code to accompany DeepMind publications