[NeurIPS 2021] Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021 Spotlight

[NeurIPS 2021] Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data

Official implementation of the NeurIPS 2021 paper "Panoptic 3D Scene Reconstruction from a Single RGB Image"

Dense Unsupervised Learning for Video Segmentation (NeurIPS*2021)

[NeurIPS 2021 Spotlight] Aligning Pretraining for Detection via Object-Level Contrastive Learning

Official implementation of CATs

Official code for "Maximum Likelihood Training of Score-Based Diffusion Models", NeurIPS 2021 (spotlight)

Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning, NeurIPS 2021 (Spotlight)

Neural Scene Flow Prior (NeurIPS 2021 spotlight)

[NeurIPS 2021] Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects

[NeurIPS 2021] Official implementation of the paper "One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective"

[NeurIPS 2021] Well-tuned Simple Nets Excel on Tabular Datasets

This repository contains the official implementation of the NeurIPS'21 paper, ROADMAP: Robust and Decomposable Average Precision for Image Retrieval.

Implementation of Neural Distance Embeddings for Biological Sequences (NeuroSEED) in PyTorch (NeurIPS 2021)

Unsupervised Part Discovery from Contrastive Reconstruction (NeurIPS 2021)

Progressive Coordinate Transforms for Monocular 3D Object Detection, NeurIPS 2021

Fast Image Retrieval (FIRe) is an open source project to promote image retrieval research. It implements most of the major binary hashing methods to date, together with different popular backbone networks and public datasets.

Code for "Learning Graph Cellular Automata" (NeurIPS 2021).

[NeurIPS 2021] ORL: Unsupervised Object-Level Representation Learning from Scene Images