[IEEE TIP 2024] Normalizing Batch Normalization for Long-Tailed Recognition

[ECCV24] VISA: Reasoning Video Object Segmentation via Large Language Model

Pytorch Implementation for CVPR 2024 paper: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation

Scenic: A Jax Library for Computer Vision Research and Beyond

Official Implementation for "StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery" (ICCV 2021 Oral)

This repository contains implementations and illustrative code to accompany DeepMind publications

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

Code for visualizing the loss landscape of neural nets

[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression

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

Implementation of Non-local Block.

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

[ECCV2020] Content-Consistent Matching for Domain Adaptive Semantic Segmentation

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

PRML algorithms implemented in Python

ACM Multimedia2020 University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization 🚁 annotates 1652 buildings in 72 universities around the world.

Pytorch implementation for few-shot photorealistic video-to-video translation.

CRF-RNN PyTorch version http://crfasrnn.torr.vision

Timeception for Complex Action Recognition, CVPR 2019 (Oral Presentation)

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Python library for Reinforcement Learning.

AVI-R Package (formerly DIVA IO): A robust reader for AVI video files

PyTorch 3D video classification models pre-trained on 65 million Instagram videos

Video Representation Learning by Dense Predictive Coding. Tengda Han, Weidi Xie, Andrew Zisserman.

Shakeout: A New Approach to Regularized Deep Neural Network Training

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

A topic-centric list of HQ open datasets.

NAS-Bench-201 API and Instruction

Tensors and Dynamic neural networks in Python with strong GPU acceleration