Data-Free Sketch-Based Image Retrieval
Abhra Chaudhuri, Ayan Kumar Bhunia, Yi-Zhe Song, Anjan Dutta

TL;DR
This paper introduces a data-free approach for sketch-based image retrieval that leverages pre-trained models without requiring paired datasets, achieving competitive results and addressing privacy concerns.
Contribution
The paper proposes the first data-free method for SBIR that uses pre-trained classification models to learn cross-modal retrieval without training data.
Findings
Outperforms existing data-free baselines significantly.
Achieves competitive mAPs compared to data-dependent methods.
Validates effectiveness on multiple benchmark datasets.
Abstract
Rising concerns about privacy and anonymity preservation of deep learning models have facilitated research in data-free learning (DFL). For the first time, we identify that for data-scarce tasks like Sketch-Based Image Retrieval (SBIR), where the difficulty in acquiring paired photos and hand-drawn sketches limits data-dependent cross-modal learning algorithms, DFL can prove to be a much more practical paradigm. We thus propose Data-Free (DF)-SBIR, where, unlike existing DFL problems, pre-trained, single-modality classification models have to be leveraged to learn a cross-modal metric-space for retrieval without access to any training data. The widespread availability of pre-trained classification models, along with the difficulty in acquiring paired photo-sketch datasets for SBIR justify the practicality of this setting. We present a methodology for DF-SBIR, which can leverage…
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.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDomain Adaptation and Few-Shot Learning · Multimodal Machine Learning Applications · Advanced Neural Network Applications
