Data-Free Sketch-Based Image Retrieval

• Published in: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 12084 - 12093
• Main Authors: Chaudhuri, Abhra, Bhunia, Ayan Kumar, Song, Yi-Zhe, Dutta, Anjan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2023
• Subjects: Data privacy; Deep learning; Design methodology; Extraterrestrial measurements; Image retrieval; Multi-modal learning; Propulsion; Training data
• DOI: 10.1109/CVPR52729.2023.01163

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 knowledge from models independently trained to perform classification on photos and sketches. We evaluate our model on the Sketchy, TU-Berlin, and QuickDraw benchmarks, designing a variety of baselines based on state-of-the-art DFL literature, and observe that our method surpasses all of them by significant margins. Our method also achieves mAPs competitive with data-dependent approaches, all the while requiring no training data. Implementation is available at https://github.com/abhrac/data-free-sbir.