SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.13990 · CVPR · 2021

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

Yongxin Yang, Tao Xiang, Yi-Zhe Song, Aneeshan Sain, Ayan Kumar Bhunia, Pinaki Chowdhury

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

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 performance 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 center 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 a significant performance boost over the state-of-theart supervised alternatives, as well as existing methods that can exploit unlabelled photos for FG-SBIR.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2103.13990")
get_code_for_paper("2103.13990")
have("2103.13990")

Connect an agent — have() is free.