Codebase for BMVC 2021 paper "Text Based Person Search with Limited Data"

Last update: Nov 24, 2022

Related tags

Deep Learning TextReID

Overview

Text Based Person Search with Limited Data

This is the codebase for our BMVC 2021 paper.

Please bear with me refactoring this codebase after CVPR deadline 😅

Abstract

Text-based person search (TBPS) aims at retrieving a target person from an image gallery with a descriptive text query. Solving such a fine-grained cross-modal retrieval task is challenging, which is further hampered by the lack of large-scale datasets. In this paper, we present a framework with two novel components to handle the problems brought by limited data. Firstly, to fully utilize the existing small-scale benchmarking datasets for more discriminative feature learning, we introduce a cross-modal momentum contrastive learning framework to enrich the training data for a given mini-batch. Secondly, we propose to transfer knowledge learned from existing coarse-grained large-scale datasets containing image-text pairs from drastically different problem domains to compensate for the lack of TBPS training data. A transfer learning method is designed so that useful information can be transferred despite the large domain gap. Armed with these components, our method achieves new state of the art on the CUHK-PEDES dataset with significant improvements over the prior art in terms of Rank-1 and mAP.

Comments

Research prepared to obtain a diploma degree in computer and Automation Engineering.

Hello!

My research focuses on Person search using Visual-Textual Attributes. Having said that, I would like to use your model to assist me in my project, but I have some issues when I finish train and test the model. My problem is trying to write code to run the model to get the same response as the photo. so Can you help me please!

opened by ram7772 6
Cannot find test_query and train_query folders
Hi @BrandonHanx

In the ReadMe file, it is mentioned to setup the datasets dir as follows:

└── cuhkpedes ├── annotations │ ├── test.json │ ├── train.json │ └── val.json ├── clip_vocab_vit.npy └── imgs ├── cam_a ├── cam_b ├── CUHK01 ├── CUHK03 ├── Market ├── test_query └── train_query

After downloading the cuhkpedes data set, we get only the imgs folder, containing cam_a, cam_b and CUHK01 folders. there is no test_query and train_query folders. Also, these folders are not in the repository. Could you provide more information regarding on these folders, more exactly, what kind of information they contain and how they must be set up?

Also, there are few more folders that are not part of the cuhkpedes, such as CUHK03 and Market. Do we need these data sets to reproduce the results?

Best regards, liviust
opened by liviust 5
some problem in training and testing

Hello

I have some problem. first: I don't find test_query and train_query file when I get images from [Dr. Shuang Li] second: I have this problem for testing and training.

opened by ram7772 4
Problem about the clip_vocab_vit.npy

Hi :) I have a question about the pre-processing document clip_vocab_vit.npy. My understanding is that it contains the tensor of the CLIP-Text-Encoder output corresponding to each word (total 9408). My question is, the output dimension of CLIP-TEXT-ENCODER is 1024, but the tensor dimension of each word in clip_vocab_vit.npy is 512. Is there some other operation in it? Thanks

opened by Frost-Yang-99 2
There is only caption_all.json in the dataset CUHK-PEDES, what are the train.json and test.json in the dataset part
Describe the bug A clear and concise description of what the bug is.

To Reproduce Steps to reproduce the behavior:

Go to '...'

Click on '....'

Scroll down to '....'

See error

Expected behavior A clear and concise description of what you expected to happen.

Screenshots If applicable, add screenshots to help explain your problem.

Desktop (please complete the following information):

OS: [e.g. iOS]

Browser [e.g. chrome, safari]

Version [e.g. 22]

Smartphone (please complete the following information):

Device: [e.g. iPhone6]

OS: [e.g. iOS8.1]

Browser [e.g. stock browser, safari]

Version [e.g. 22]

Additional context Add any other context about the problem here.
opened by SwimKY 1

Releases(v0.1.1)

v0.1.1(Dec 10, 2021)

Full Changelog: https://github.com/BrandonHanx/TextReID/compare/v0.1.0...v0.1.1
Source code(tar.gz)
Source code(zip)

Owner

Xiao Han

Ph.D. student @ UoSurrey CVSSP, B.Eng. @ ZJU ISEE

GitHub Repository

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

English | 简体中文 | 繁體中文 State-of-the-art Natural Language Processing for Jax, PyTorch and TensorFlow 🤗 Transformers provides thousands of pretrained mo

77.2k Jan 02, 2023

PyTorch implementation of Soft-DTW: a Differentiable Loss Function for Time-Series in CUDA

Soft DTW Loss Function for PyTorch in CUDA This is a Pytorch Implementation of Soft-DTW: a Differentiable Loss Function for Time-Series which is batch

76 Dec 20, 2022

NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch

PyTorch implementation of Normalizer-Free Networks and SGD - Adaptive Gradient Clipping Paper: https://arxiv.org/abs/2102.06171.pdf Original code: htt

320 Jan 02, 2023

Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation

Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation Introduction 📋 Official implementation of Explainable Robust Learnin

6 Apr 19, 2022

[CVPR 2022] Official code for the paper: "A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration"

MDCA Calibration This is the official PyTorch implementation for the paper: "A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved

21 Dec 22, 2022

Official implementation for the paper: Generating Smooth Pose Sequences for Diverse Human Motion Prediction

Generating Smooth Pose Sequences for Diverse Human Motion Prediction This is official implementation for the paper Generating Smooth Pose Sequences fo

28 Dec 10, 2022

This is Official implementation for "Pose-guided Feature Disentangling for Occluded Person Re-Identification Based on Transformer" in AAAI2022

PFD：Pose-guided Feature Disentangling for Occluded Person Re-identification based on Transformer This repo is the official implementation of "Pose-gui

93 Dec 18, 2022

Experimenting with computer vision techniques to generate annotated image datasets from gameplay recordings automatically.

Experimenting with computer vision techniques to generate annotated image datasets from gameplay recordings automatically. The collected data will then be used to train a deep neural network that can

3 Apr 24, 2022

This repository contains the code for our paper VDA (public in EMNLP2021 main conference)

Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models This repository contains the code for our paper VDA (publ

13 Aug 06, 2022

VACA: Designing Variational Graph Autoencoders for Interventional and Counterfactual Queries

VACA Code repository for the paper "VACA: Designing Variational Graph Autoencoders for Interventional and Counterfactual Queries (arXiv)". The impleme

16 Oct 10, 2022

A Dying Light 2 (DL2) PAKFile Utility for Modders and Mod Makers.

Dying Light 2 PAKFile Utility A Dying Light 2 (DL2) PAKFile Utility for Modders and Mod Makers. This tool aims to make PAKFile (.pak files) modding a

12 Aug 26, 2022

Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing

Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing Paper Introduction Multi-task indoor scene understanding is widely considered a

62 Dec 05, 2022

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

face.evoLVe: High-Performance Face Recognition Library based on PaddlePaddle & PyTorch Evolve to be more comprehensive, effective and efficient for fa

3.1k Jan 04, 2023

Code for the paper "Unsupervised Contrastive Learning of Sound Event Representations", ICASSP 2021.

Unsupervised Contrastive Learning of Sound Event Representations This repository contains the code for the following paper. If you use this code or pa

81 Dec 22, 2022

Deep Learning Interviews book: Hundreds of fully solved job interview questions from a wide range of key topics in AI.

This book was written for you: an aspiring data scientist with a quantitative background, facing down the gauntlet of the interview process in an increasingly competitive field. For most of you, the

4.1k Dec 28, 2022

Code accompanying our NeurIPS 2021 traffic4cast challenge

Traffic forecasting on traffic movie snippets This repo contains all code to reproduce our approach to the IARAI Traffic4cast 2021 challenge. In the c

2 Aug 09, 2022

VolumeGAN - 3D-aware Image Synthesis via Learning Structural and Textural Representations

VolumeGAN - 3D-aware Image Synthesis via Learning Structural and Textural Representations 3D-aware Image Synthesis via Learning Structural and Textura

116 Dec 26, 2022

Awesome Weak-Shot Learning

Awesome Weak-Shot Learning In weak-shot learning, all categories are split into non-overlapped base categories and novel categories, in which base cat

162 Dec 30, 2022

Learning from Synthetic Humans, CVPR 2017

Learning from Synthetic Humans (SURREAL) Gül Varol, Javier Romero, Xavier Martin, Naureen Mahmood, Michael J. Black, Ivan Laptev and Cordelia Schmid,

538 Dec 18, 2022

Code & Models for Temporal Segment Networks (TSN) in ECCV 2016

Temporal Segment Networks (TSN) We have released MMAction, a full-fledged action understanding toolbox based on PyTorch. It includes implementation fo

1.4k Jan 01, 2023