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

A simple rest api serving a deep learning model that classifies human gender based on their faces. (vgg16 transfare learning)

this is a simple rest api serving a deep learning model that classifies human gender based on their faces. (vgg16 transfare learning)

5 Dec 09, 2021

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

Related tags

Overview

Text Based Person Search with Limited Data

Abstract

Comments

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

Cannot find test_query and train_query folders

some problem in training and testing

Problem about the clip_vocab_vit.npy

There is only caption_all.json in the dataset CUHK-PEDES, what are the train.json and test.json in the dataset part

Releases(v0.1.1)

v0.1.1(Dec 10, 2021)

Owner

Xiao Han

Advances in Neural Information Processing Systems (NeurIPS), 2020.

In-place Parallel Super Scalar Samplesort (IPS⁴o)

Official repository of the paper Privacy-friendly Synthetic Data for the Development of Face Morphing Attack Detectors

Pytorch0.4.1 codes for InsightFace

FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks

YolactEdge: Real-time Instance Segmentation on the Edge

This is a TensorFlow implementation for C2-Rec

Official Matlab Implementation for "Tiny Obstacle Discovery by Occlusion-aware Multilayer Regression", TIP 2020

Py4fi2nd - Jupyter Notebooks and code for Python for Finance (2nd ed., O'Reilly) by Yves Hilpisch.

Using Language Model to Bootstrap Human Activity Recognition Ambient Sensors Based in Smart Homes

The repository offers the official implementation of our paper in PyTorch.

The implementation our EMNLP 2021 paper "Enhanced Language Representation with Label Knowledge for Span Extraction".

Streaming Anomaly Detection Framework in Python (Outlier Detection for Streaming Data)

Seeing if I can put together an interactive version of 3b1b's Manim in Streamlit

Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It Efficiently

General purpose Slater-Koster tight-binding code for electronic structure calculations

This project uses Template Matching technique for object detecting by detection of template image over base image.

PyBrain - Another Python Machine Learning Library.

Code for A Volumetric Transformer for Accurate 3D Tumor Segmentation

A simple rest api serving a deep learning model that classifies human gender based on their faces. (vgg16 transfare learning)