A clustering method I have worked on in the past. Compatible with the SciKitLearn framework.

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

"Describing Textures using Natural Language" code and data, ECCV 2020 Oral.

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Self-supervised vIsion Transformer (SiT)

This is the official released code for our paper, The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos, which has been accepted by NeurIPS 2021.

Anomaly Detection in Video via Self-Supervised and Multi-Task Learning

The PASS dataset: pretrained models and how to get the data

Tutorial about 3D convolutional network

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.

Lightweight image sequence visualization utility based on matplotlib

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

Visualizer for Deep Neural Networks

Semi-Supervised Robust Deep Neural Networks for Multi-Label Classification

Transformer Tracking (CVPR2021)

Siamese and triplet networks with online pair/triplet mining in PyTorch

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose (CVPR 2021)

(CVPR 2021 Oral) Open World Object Detection

🎓 Path to a free self-taught education in Computer Science!

Implementation of the Object Relation Transformer for Image Captioning

Implementation of Linear Regression Model using the Normal Equation (Closed-form solution) and the Gradient Descent Algorithm (Open-form solution))

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

This code package implements the prototypical part network (ProtoPNet) from the paper "This Looks Like That: Deep Learning for Interpretable Image Recognition" (to appear at NeurIPS 2019), by Chaof…

This is code going with the paper "The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation" (CVPR 2018)

official implementation for the paper "Simplifying Graph Convolutional Networks"

Pytorch implementation of our T-PAMI 2021 paper: Self-supervised Video Representation Learning by Uncovering Motion and Appearance Statistics

code for CVPR-2019 paper: Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics