game-feature-learningCode for paper "Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery", Ren et al., CVPR'18
Stars: ✭ 68 (+28.3%)
IAST-ECCV2020IAST: Instance Adaptive Self-training for Unsupervised Domain Adaptation (ECCV 2020) https://teacher.bupt.edu.cn/zhuchuang/en/index.htm
Stars: ✭ 84 (+58.49%)
G-SFDAcode for our ICCV 2021 paper 'Generalized Source-free Domain Adaptation'
Stars: ✭ 88 (+66.04%)
DAOSLImplementation of Domain Adaption in One-Shot Learning
Stars: ✭ 14 (-73.58%)
SSTDA[CVPR 2020] Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation (PyTorch)
Stars: ✭ 150 (+183.02%)
meta-learning-progressRepository to track the progress in Meta-Learning (MtL), including the datasets and the current state-of-the-art for the most common MtL problems.
Stars: ✭ 26 (-50.94%)
Learning Via TranslationImage-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification (https://arxiv.org/pdf/1711.07027.pdf). CVPR2018
Stars: ✭ 202 (+281.13%)
Dann py3python 3 pytorch implementation of DANN
Stars: ✭ 164 (+209.43%)
smognSynthetic Minority Over-Sampling Technique for Regression
Stars: ✭ 238 (+349.06%)
DCAN[AAAI 2020] Code release for "Domain Conditioned Adaptation Network" https://arxiv.org/abs/2005.06717
Stars: ✭ 27 (-49.06%)
gplPowerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval" https://arxiv.org/abs/2112.07577
Stars: ✭ 216 (+307.55%)
CAC-UNet-DigestPath20191st to MICCAI DigestPath2019 challenge (https://digestpath2019.grand-challenge.org/Home/) on colonoscopy tissue segmentation and classification task. (MICCAI 2019) https://teacher.bupt.edu.cn/zhuchuang/en/index.htm
Stars: ✭ 83 (+56.6%)
SegSwap(CVPRW 2022) Learning Co-segmentation by Segment Swapping for Retrieval and Discovery
Stars: ✭ 46 (-13.21%)
DASCode and datasets for EMNLP2018 paper ‘‘Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification’’.
Stars: ✭ 48 (-9.43%)
TA3N[ICCV 2019 Oral] TA3N: https://github.com/cmhungsteve/TA3N (Most updated repo)
Stars: ✭ 45 (-15.09%)
IntradaUnsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision (CVPR 2020 Oral)
Stars: ✭ 211 (+298.11%)
genalogGenalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.
Stars: ✭ 234 (+341.51%)
CrstCode for <Confidence Regularized Self-Training> in ICCV19 (Oral)
Stars: ✭ 177 (+233.96%)
CrossNERCrossNER: Evaluating Cross-Domain Named Entity Recognition (AAAI-2021)
Stars: ✭ 87 (+64.15%)
mtss-ganMTSS-GAN: Multivariate Time Series Simulation with Generative Adversarial Networks (by @firmai)
Stars: ✭ 77 (+45.28%)
Squeezesegv2Implementation of SqueezeSegV2, Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
Stars: ✭ 154 (+190.57%)
Dta.pytorchOfficial implementation of Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation, to be presented at ICCV 2019.
Stars: ✭ 144 (+171.7%)
Deep-Unsupervised-Domain-AdaptationPytorch implementation of four neural network based domain adaptation techniques: DeepCORAL, DDC, CDAN and CDAN+E. Evaluated on benchmark dataset Office31.
Stars: ✭ 50 (-5.66%)
Transferable-E2E-ABSATransferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning (EMNLP'19)
Stars: ✭ 62 (+16.98%)
FixBiFixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation (CVPR 2021)
Stars: ✭ 48 (-9.43%)
AdaptationSegCurriculum Domain Adaptation for Semantic Segmentation of Urban Scenes, ICCV 2017
Stars: ✭ 128 (+141.51%)
pykaleKnowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for interdisciplinary research, part of the 🔥PyTorch ecosystem
Stars: ✭ 381 (+618.87%)
multi-task-defocus-deblurring-dual-pixel-nimatReference github repository for the paper "Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning". We propose a single-image deblurring network that incorporates the two sub-aperture views into a multitask framework. Specifically, we show that jointly learning to predict the two DP views from a single …
Stars: ✭ 29 (-45.28%)
transfertoolsPython toolbox for transfer learning.
Stars: ✭ 22 (-58.49%)
BA3UScode for our ECCV 2020 paper "A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation"
Stars: ✭ 31 (-41.51%)
pytorch-revgradA minimal pytorch package implementing a gradient reversal layer.
Stars: ✭ 142 (+167.92%)
DeepEchoSynthetic Data Generation for mixed-type, multivariate time series.
Stars: ✭ 44 (-16.98%)
MGANExploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification (AAAI'19)
Stars: ✭ 44 (-16.98%)
SFAOfficial Implementation of "Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers"
Stars: ✭ 79 (+49.06%)
Clan( CVPR2019 Oral ) Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
Stars: ✭ 248 (+367.92%)
DA-RetinaNetOfficial Detectron2 implementation of DA-RetinaNet of our Image and Vision Computing 2021 work 'An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites'
Stars: ✭ 31 (-41.51%)
Ta3n[ICCV 2019 (Oral)] Temporal Attentive Alignment for Large-Scale Video Domain Adaptation (PyTorch)
Stars: ✭ 217 (+309.43%)
BadMedicineLibrary and CLI for randomly generating medical data like you might get out of an Electronic Health Records (EHR) system
Stars: ✭ 18 (-66.04%)
Seg UncertaintyIJCAI2020 & IJCV 2020 🌇 Unsupervised Scene Adaptation with Memory Regularization in vivo
Stars: ✭ 202 (+281.13%)
SDGymBenchmarking synthetic data generation methods.
Stars: ✭ 177 (+233.96%)
Bnmcode of Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations (CVPR2020 oral)
Stars: ✭ 192 (+262.26%)
Self Similarity GroupingSelf-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification (ICCV 2019, Oral)
Stars: ✭ 171 (+222.64%)
ACANCode for NAACL 2019 paper: Adversarial Category Alignment Network for Cross-domain Sentiment Classification
Stars: ✭ 23 (-56.6%)
FAST-RIRThis is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment.
Stars: ✭ 90 (+69.81%)
CbstCode for <Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training> in ECCV18
Stars: ✭ 146 (+175.47%)
gretel-python-clientThe Gretel Python Client allows you to interact with the Gretel REST API.
Stars: ✭ 28 (-47.17%)
Cdcl Human Part SegmentationRepository for Paper: Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation (TCSVT20)
Stars: ✭ 143 (+169.81%)
visda2019-multisourceSource code of our submission (Rank 1) for Multi-Source Domain Adaptation task in VisDA-2019
Stars: ✭ 49 (-7.55%)
table-evaluatorEvaluate real and synthetic datasets with each other
Stars: ✭ 44 (-16.98%)
DualStudentCode for Paper ''Dual Student: Breaking the Limits of the Teacher in Semi-Supervised Learning'' [ICCV 2019]
Stars: ✭ 106 (+100%)
zpySynthetic data for computer vision. An open source toolkit using Blender and Python.
Stars: ✭ 251 (+373.58%)
synthThe Declarative Data Generator
Stars: ✭ 958 (+1707.55%)