Self-Supervised Pre-Training for Transformer-Based Person Re-Identification [pdf]
The official repository for Self-Supervised Pre-Training for Transformer-Based Person Re-Identification. Code and model will be uploaded when ready.
Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
Overview
Comments
-
speed of training
opened by wengdunfang 5Hi ,when I using python -W ignore -m torch.distributed.launch --nproc_per_node=8 main_dino.py
--arch vit_small
--data_path /my path/LUP
--output_dir ./log/dino/lup/vit_small_full_lup
--height 256 --width 128
--crop_height 128 --crop_width 64
--epochs 100 \I found my code stuck at line 153 (main_dino. Py). Is this caused by loading the luperson dataset? It's been running for six hours.
-
请问使用LUPerson进行pretrain时，LUPerson的数据集文件结构是什么样的？
opened by siyuch-fdu 2非常感谢您的工作！ 我想使用您的DINO代码对LUPerson进行预训练，我看到您的代码好像是将LUPerson里边的数据以图片的形式直接load（main_dino.py line153:
dataset = datasets.ImageFolder(args.data_path, transform=transform)）。但是我拿到的LUPerson数据集是.mdb格式的，没办法直接读取。想问下我是否需要将.mdb格式的数据集转换成.jpg图片？如果需要的话，转换后的LUPerson数据集的组织形式是什么样的？（从main_dino.py line158:dir_path = os.path.join(args.data_path,'images')看到似乎LUPerson文件夹下还有‘images’文件夹）希望您能帮助我解决这个问题，万分感谢！
-
Performance on Domain Generalization
opened by liyuke65535 2Thanks for your works on ReID! I got several questions:
- I see you've done UDA experiments between market and msmt in TransReID-SSL. What if just train the model on A person-dataset then test on B person-dataset? How's the performance?
- What does 'patchify stem' mean? More specifically, what's the purpose of ICS component and where it works?
-
About how to process LUP dataset
opened by whobefore 2Excellent work! And how you process dets.pkl of LUP dataset? It seems that the video extraction has resolution problem and we don't know the FPS. If you have done it, could you send me the script? Thanks a lot!
-
this model is overfitting to other dataset ?
opened by joynjo 0I try to implement this model, but the result is very bad when applied to other unknown dataset. Is there any specific setting? or the model is overfitting ?
-
`compute_jaccard_distance` function failing on multi-gpu
opened by toshalpatel 0Using
compute_jaccard_distancefunction defined in faiss_rerank.py. Thesearch_optionvariable is hard coded to 2, which uses multiple GPUs if the machine has any.The final jaccard distance is incorrect as each value is the same (some number), whereas when i use
search_option = None, i.e., CPU option, the jaccard distance makes sense.I am using RTX 3090 GPU.
Can you please help me check if there is some issue? Thanks!
Large-Scale Pre-training for Person Re-identification with Noisy Labels (LUPerson-NL)
LUPerson-NL Large-Scale Pre-training for Person Re-identification with Noisy Labels (LUPerson-NL) The repository is for our CVPR2022 paper Large-Scale
43 Dec 26, 2022
[CVPR 2021] "The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models" Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Michael Carbin, Zhangyang Wang
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models Codes for this paper The Lottery Tickets Hypo
59 Dec 28, 2022
Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR
UniSpeech The family of UniSpeech: UniSpeech (ICML 2021): Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR UniSpeech-
282 Jan 9, 2023
Implementation of "Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification"
hypergraph_reid Implementation of "Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification" If you find this help your research,
62 Dec 21, 2022
PyTorch implementation of "Contrast to Divide: self-supervised pre-training for learning with noisy labels"
Contrast to Divide: self-supervised pre-training for learning with noisy labels This is an official implementation of "Contrast to Divide: self-superv
55 Nov 23, 2022
UniLM AI - Large-scale Self-supervised Pre-training across Tasks, Languages, and Modalities
Pre-trained (foundation) models across tasks (understanding, generation and translation), languages (100+ languages), and modalities (language, image, audio, vision + language, audio + language, etc.)
7.6k Jan 1, 2023
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training [Arxiv] VideoMAE: Masked Autoencoders are Data-Efficient Learne
697 Jan 7, 2023
The Self-Supervised Learner can be used to train a classifier with fewer labeled examples needed using self-supervised learning.
Published by SpaceML • About SpaceML • Quick Colab Example Self-Supervised Learner The Self-Supervised Learner can be used to train a classifier with
92 Nov 30, 2022
offical implement of our Lifelong Person Re-Identification via Adaptive Knowledge Accumulation in CVPR2021
LifelongReID Offical implementation of our Lifelong Person Re-Identification via Adaptive Knowledge Accumulation in CVPR2021 by Nan Pu, Wei Chen, Yu L
76 Dec 8, 2022
[TIP2020] Adaptive Graph Representation Learning for Video Person Re-identification
Introduction This is the PyTorch implementation for Adaptive Graph Representation Learning for Video Person Re-identification. Get started git clone h
41 Dec 12, 2022
[CVPR-2021] UnrealPerson: An adaptive pipeline for costless person re-identification
UnrealPerson: An Adaptive Pipeline for Costless Person Re-identification In our paper (arxiv), we propose a novel pipeline, UnrealPerson, that decreas
70 Oct 10, 2022
IAUnet: Global Context-Aware Feature Learning for Person Re-Identification
IAUnet This repository contains the code for the paper: IAUnet: Global Context-Aware Feature Learning for Person Re-Identification Ruibing Hou, Bingpe
30 Jul 14, 2022
Person Re-identification
Person Re-identification Final project of Computer Vision Table of content Person Re-identification Table of content Students: Proposed method Dataset
4 Jun 17, 2021
Experiment about Deep Person Re-identification with EfficientNet-v2
We evaluated the baseline with Resnet50 and Efficienet-v2 without using pretrained models. Also Resnet50-IBN-A and Efficientnet-v2 using pretrained on ImageNet. We used two datasets: Market-1501 and CUHK03.
77 Jan 3, 2023
Torchreid: Deep learning person re-identification in PyTorch.
Torchreid Torchreid is a library for deep-learning person re-identification, written in PyTorch. It features: multi-GPU training support both image- a
3.7k Jan 5, 2023
Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral)
Joint Discriminative and Generative Learning for Person Re-identification [Project] [Paper] [YouTube] [Bilibili] [Poster] [Supp] Joint Discriminative
1.2k Dec 30, 2022
CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification (ICCV2021)
CM-NAS Official Pytorch code of paper CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification in ICCV2021. Vis
40 Nov 25, 2022
[BMVC2021] The official implementation of "DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations"
DomainMix [BMVC2021] The official implementation of "DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations" [paper] [de
17 Dec 20, 2022
Exploiting Robust Unsupervised Video Person Re-identification
Exploiting Robust Unsupervised Video Person Re-identification Implementation of the proposed uPMnet. For the preprint, please refer to [Arxiv]. Gettin
1 Apr 9, 2022