More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval

Overview

More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval, CVPR 2021.

Ayan Kumar Bhunia, Pinaki nath Chowdhury, Aneeshan Sain, Yongxin Yang, Tao Xiang, Yi-Zhe Song, “More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval”, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2021.

SketchX_ShoeV2/ChairV2 Dataset: Download

Abstract

A fundamental challenge faced by existing Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) models is the data scarcity -- model performances are largely bottlenecked by the lack of sketch-photo pairs. Whilst the number of photos can be easily scaled, each corresponding sketch still needs to be individually produced. In this paper, we aim to mitigate such an upper-bound on sketch data, and study whether unlabelled photos alone (of which they are many) can be cultivated for performances gain. In particular, we introduce a novel semi-supervised framework for cross-modal retrieval that can additionally leverage large-scale unlabelled photos to account for data scarcity. At the centre of our semi-supervision design is a sequential photo-to-sketch generation model that aims to generate paired sketches for unlabelled photos. Importantly, we further introduce a discriminator guided mechanism to guide against unfaithful generation, together with a distillation loss based regularizer to provide tolerance against noisy training samples. Last but not least, we treat generation and retrieval as two conjugate problems, where a joint learning procedure is devised for each module to mutually benefit from each other. Extensive experiments show that our semi-supervised model yields significant performance boost over the state-of-the-art supervised alternatives, as well as existing methods that can exploit unlabelled photos for FG-SBIR.

Outline

Outline

Figure: Our proposed method additionally leverages large scale photos without any manually labelled paired sketches to improve FG-SBIR performance. Moreover, we show that the two conjugate process, photo-to-sketch generation and fine-grained SBIR, could improve each other by joint training.

Joint Architecture

Framework Figure: Our framework: a FG-SBIR model leverages large scale unlabelled photos using a sequential photo-to-sketch generation model along with labelled pairs. Discriminator guided instance-wise weighting and distillation loss are used to guard against the noisy generated data. Simultaneously, photo-to-sketch generation model learns by taking reward from FG-SBIR model and Discriminator via policy gradient (over both labelled and unlabelled) together with supervised VAE loss over labelled data. Note rasterization (vector to raster format) is a non-differentiable operation.

Examples

Framework Figure: Qualitative results on our photo-to-sketch generation process, where sketch is shown with attention-map at progressive instances.

Citation

If you find this article useful in your research, please consider citing:

@InProceedings{semi-fgsbir,
author = {Ayan Kumar Bhunia and Pinaki Nath Chowdhury and Aneeshan Sain and Yongxin Yang and Tao Xiang and Yi-Zhe Song},
title = {More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021}
}

Work done at SketchX Lab, CVSSP, University of Surrey.

Owner
Ayan Kumar Bhunia
I am a PhD student, focussing on Computer Vision and Deep Learning, at Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey.
Ayan Kumar Bhunia
Image Segmentation Evaluation

Image Segmentation Evaluation Martin Keršner, [email protected] Evaluation

Martin Kersner 273 Oct 28, 2022
MCMC samplers for Bayesian estimation in Python, including Metropolis-Hastings, NUTS, and Slice

Sampyl May 29, 2018: version 0.3 Sampyl is a package for sampling from probability distributions using MCMC methods. Similar to PyMC3 using theano to

Mat Leonard 304 Dec 25, 2022
This repository is the official implementation of Open Rule Induction. This paper has been accepted to NeurIPS 2021.

Open Rule Induction This repository is the official implementation of Open Rule Induction. This paper has been accepted to NeurIPS 2021. Abstract Rule

Xingran Chen 16 Nov 14, 2022
This is the codebase for Diffusion Models Beat GANS on Image Synthesis.

This is the codebase for Diffusion Models Beat GANS on Image Synthesis.

OpenAI 3k Dec 26, 2022
Scenarios, tutorials and demos for Autonomous Driving

The Autonomous Driving Cookbook (Preview) NOTE: This project is developed and being maintained by Project Road Runner at Microsoft Garage. This is cur

Microsoft 2.1k Jan 02, 2023
Oriented Object Detection: Oriented RepPoints + Swin Transformer/ReResNet

Oriented RepPoints for Aerial Object Detection The code for the implementation of “Oriented RepPoints + Swin Transformer/ReResNet”. Introduction Based

96 Dec 13, 2022
Jaxtorch (a jax nn library)

Jaxtorch (a jax nn library) This is my jax based nn library. I created this because I was annoyed by the complexity and 'magic'-ness of the popular ja

nshepperd 17 Dec 08, 2022
Vpw analyzer - A visual J1850 VPW analyzer written in Python

VPW Analyzer A visual J1850 VPW analyzer written in Python Requires Tkinter, Pan

7 May 01, 2022
Ludwig is a toolbox that allows to train and evaluate deep learning models without the need to write code.

Translated in 🇰🇷 Korean/ Ludwig is a toolbox that allows users to train and test deep learning models without the need to write code. It is built on

Ludwig 8.7k Jan 05, 2023
Deep learning with dynamic computation graphs in TensorFlow

TensorFlow Fold TensorFlow Fold is a library for creating TensorFlow models that consume structured data, where the structure of the computation graph

1.8k Dec 28, 2022
Code in PyTorch for the convex combination linear IAF and the Householder Flow, J.M. Tomczak & M. Welling

VAE with Volume-Preserving Flows This is a PyTorch implementation of two volume-preserving flows as described in the following papers: Tomczak, J. M.,

Jakub Tomczak 87 Dec 26, 2022
[NeurIPS 2021] A weak-shot object detection approach by transferring semantic similarity and mask prior.

TransMaS This repository is the official pytorch implementation of the following paper: NIPS2021 Mixed Supervised Object Detection by TransferringMask

BCMI 49 Jul 27, 2022
EPSANet:An Efficient Pyramid Split Attention Block on Convolutional Neural Network

EPSANet:An Efficient Pyramid Split Attention Block on Convolutional Neural Network This repo contains the official Pytorch implementaion code and conf

Hu Zhang 175 Jan 07, 2023
DaReCzech is a dataset for text relevance ranking in Czech

Dataset DaReCzech is a dataset for text relevance ranking in Czech. The dataset consists of more than 1.6M annotated query-documents pairs,

Seznam.cz a.s. 8 Jul 26, 2022
Supplementary materials for ISMIR 2021 LBD paper "Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes"

Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes Supplementary materials for ISMIR 2021 LBD submission: K. N. W

Karn Watcharasupat 2 Oct 25, 2021
Towards Understanding Quality Challenges of the Federated Learning: A First Look from the Lens of Robustness

FL Analysis This repository contains the code and results for the paper "Towards Understanding Quality Challenges of the Federated Learning: A First L

3 Oct 17, 2022
Data augmentation for NLP, accepted at EMNLP 2021 Findings

AEDA: An Easier Data Augmentation Technique for Text Classification This is the code for the EMNLP 2021 paper AEDA: An Easier Data Augmentation Techni

Akbar Karimi 81 Dec 09, 2022
Static Features Classifier - A static features classifier for Point-Could clusters using an Attention-RNN model

Static Features Classifier This is a static features classifier for Point-Could

ABDALKARIM MOHTASIB 1 Jan 25, 2022
Deep Learning for Computer Vision final project

Deep Learning for Computer Vision final project

grassking100 1 Nov 30, 2021
public repo for ESTER dataset and modeling (EMNLP'21)

Project / Paper Introduction This is the project repo for our EMNLP'21 paper: https://arxiv.org/abs/2104.08350 Here, we provide brief descriptions of

PlusLab 19 Oct 27, 2022