An Efficient Framework for Zero-Shot Sketch-Based Image Retrieval
Osman Tursun, Simon Denman, Sridha Sridharan, Ethan Goan, Clinton, Fookes

TL;DR
This paper introduces a simple, resource-efficient zero-shot sketch-based image retrieval framework that leverages a single CNN and novel loss functions, eliminating the need for complex models and semantic labels.
Contribution
It proposes a novel, lightweight framework for ZS-SBIR that does not depend on multiple CNNs or semantic labels, improving efficiency and practicality.
Findings
Achieves competitive retrieval accuracy with reduced computational resources.
Uses a single pre-trained CNN fine-tuned with novel loss functions.
Eliminates the need for semantic categorical labels during training.
Abstract
Recently, Zero-shot Sketch-based Image Retrieval (ZS-SBIR) has attracted the attention of the computer vision community due to it's real-world applications, and the more realistic and challenging setting than found in SBIR. ZS-SBIR inherits the main challenges of multiple computer vision problems including content-based Image Retrieval (CBIR), zero-shot learning and domain adaptation. The majority of previous studies using deep neural networks have achieved improved results through either projecting sketch and images into a common low-dimensional space or transferring knowledge from seen to unseen classes. However, those approaches are trained with complex frameworks composed of multiple deep convolutional neural networks (CNNs) and are dependent on category-level word labels. This increases the requirements on training resources and datasets. In comparison, we propose a simple and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Image and Video Retrieval Techniques · Domain Adaptation and Few-Shot Learning · Multimodal Machine Learning Applications
