Projects sharing features with Caffe

The implement of "Learning Disentangled Semantic Representation for Domain Adaptation" (IJCAI 2019)

SBADA-GAN CVPR 2018 code This is a preliminary release, as the code needs a massive cleanup being extremely verbose in this current state. In the Mnist_MnistM notebook can be found an example of how to run SBADA-GAN on Mnist -> MnistM Domain Adaptation task.

This code requires Python 3, and is implemented in Tensorflow.

We release paper and code for SwAV, our new self-supervised method. SwAV pushes self-supervised learning to only 1.2% away from supervised learning on ImageNet with a ResNet-50! It combines online clustering with a multi-crop data augmentation.

DeiT is a PyTorch vision transformer framework designed for image classification. It implements a transformer-based architecture that processes images as sequences of flattened patches using self-attention layers and position-aware sequence modeling instead of convolutional filters. The project focuses on data-efficient training through a knowledge distillation framework. This system allows a student model to mimic the soft labels of a high-performance teacher model to improve accuracy and generalization, particularly when training on smaller datasets. The library covers the full development

This project is a PyTorch vision transformer framework designed for self-supervised learning. It implements a model that trains visual representations using a momentum teacher and self-distillation without the need for labeled data. The library functions as an image feature extractor and visual attention visualizer, allowing for the generation of high-dimensional vectors and the rendering of self-attention maps as heatmaps or videos to analyze model focus. It provides comprehensive tools for downstream vision evaluation, including linear probe classification, k-nearest neighbor categorizatio

moco is a PyTorch implementation of momentum contrast designed for self-supervised visual representation learning. It serves as a research-based framework for extracting high-level image features from unlabeled datasets by maximizing the similarity between different views of the same image. The system utilizes an asymmetric encoder architecture consisting of a fast-learning online encoder and a slow-evolving momentum encoder to stabilize training. It employs a dictionary-based approach that compares query images against a dynamic queue of negative samples to learn distinguishing visual featur

PyTorch implementation of SimSiam https//arxiv.org/abs/2011.10566

PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

pytorch implementation of Domain-Adversarial Training of Neural Networks

A simple method to perform semi-supervised learning with limited data.

Code for the paper: "MixMatch - A Holistic Approach to Semi-Supervised Learning" by David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver and Colin Raffel.

Code for Noisy Student Training. https://arxiv.org/abs/1911.04252

This project is a self-supervised contrastive learning framework designed to train deep learning models to learn visual representations from images without using human-provided labels. It provides a system for developing pretrained visual representation models that can be adapted for downstream computer vision tasks. The framework includes tools for semi-supervised image classification, which combines large unlabeled datasets with small labeled sets to improve accuracy. It also features a linear probe evaluation tool to assess the quality of learned image features by training a simple linear

This code was developed based on dirt-t.

Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling

arXiv 2019 "Contrastive Multiview Coding", also contains implementations for MoCo and InstDis

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

Code release for Discriminative Adversarial Domain Adaptation (AAAI2020).

Domain Adaptation Based on the Triplet Loss

Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"

(ECCV 2020) Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation

A collection of implementations of adversarial domain adaptation algorithms