👀 | MobileGaze: Gaze Estimation models using ResNet 18/34/50, MobileNet v2 and MobileOne s0-s4 | In PyTorch >> ONNX

PyTorch implementation for Contrastive Representation Learning for Gaze Estimation

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

Code that accompanies the paper Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning - Accepted to ICML2024

[CVPR 2024 Highlight] Logit Standardization in Knowledge Distillation

Source Code of the paper "Achievement based Training Progress Balancing for Multi-Task Learning" accepted in ICCV2023

A curated (most recent) list of resources for Learning with Noisy Labels

Can GPT-4 Perform Neural Architecture Search?

A PyTorch Library for Multi-Task Learning

Code for fitting masks to face images in the wild

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) fo…

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

The implementation of the technical report: "Customized Segment Anything Model for Medical Image Segmentation"

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

This is the official implementation of the Video Dialog as Conversation about Objects Living in Space-Time paper

A new paradigm for privacy-presevering face recognition.

Code release for ConvNeXt model

Efficient facial landmark detector

Bringing Old Photo Back to Life (CVPR 2020 oral)

A coding-free framework built on PyTorch for reproducible deep learning studies. 🏆25 knowledge distillation methods presented at CVPR, ICLR, ECCV, NeurIPS, ICCV, etc are implemented so far. 🎁 Train…

Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images (ICCV 2021)

State-of-the-art 2D and 3D Face Analysis Project

Towards End-to-end Video-based Eye-tracking. ECCV 2020. https://ait.ethz.ch/eve

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

A Data Platform for Medical AI that enables building high-quality datasets and algorithms with lean process and advanced annotation features.

The official implementation of ICLR2021 paper "Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient Detectors".

The official PyTorch implementation of img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation - CVPR 2021

Bottleneck Transformers for Visual Recognition

COVID deterioration prediction based on chest X-ray radiographs via MoCo-trained image representations

Official SRFlow training code: Super-Resolution using Normalizing Flow in PyTorch