Home > Published Issues > 2024 > Volume 15, No. 3, 2024 >
JAIT 2024 Vol.15(3): 364-371
doi: 10.12720/jait.15.3.364-371

Good Teacher Makes Good Student: A Discriminative-Aware Knowledge Preservation Approach for Zero-Shot Sketch-Based Image Retrieval

Haifeng Zhao 1,2,3,*, Tianjian Wu 1,3,4, Yuting Tao 1,3, and Yan Zhang 1,3
1. School of Software Engineering, Jinling Institute of Technology, Nanjing, China
2. Jiangsu Hoperun Software Co. Ltd., Nanjing, China
3. Information Analysis Engineering Research Center of Jiangsu Province, Nanjing, China
4. School of Computer and Electronic Information, Nanjing Normal University, Nanjing, China
Email: zhf@jit.edu.cn (H.Z.), wutianjian@eswincomputing.com (T.W.), tao_yuting@jit.edu.cn (Y.T.), zy@jit.edu.cn (Y.Z.)
*Corresponding author

Manuscript received September 22, 2023; revised October 12, 2023; accepted October 31, 2023; published March 14, 2024.

Abstract—Sketch-Based Image Retrieval (SBIR) is widely used in animation, e-commerce, and security. In these real-world applications, the classes of retrieval may be very different from the training classes, making it a zero-shot SBIR problem. Most methods in the literature resort to bridging the semantic gap between the sketch and image domains by learning a common space with a pre-trained model on a large dataset as the base network, and then fine-tuning on the target SBIR datasets. In this process, the acquired knowledge of the pre-trained model may be lost, resulting in performance degradation. To tackle this problem, we propose a teacher-student network architecture, which consists of a teacher network using the pre-trained model and a student network whose output is guided by the teacher network. Instead of introducing supplementary semantics in the teacher network, we adopt a more powerful pre-trained model as the teacher network and further enhance its discriminative capability by adding a hard-coded margin based on the prediction probability. The student network is then fine-tuned by using the teacher network’s output as the learning target. Experiments on two benchmark datasets show that the proposed approach outperforms the state-of-the-art methods by more than 10%, which verifies that the prior knowledge can be better preserved by a good teacher network, which can make the student network good too.
Keywords—Sketch-Based Image Retrieval (SBIR), zero-shot, knowledge preservation

Cite: Haifeng Zhao, Tianjian Wu, Yuting Tao, and Yan Zhang, "Good Teacher Makes Good Student: A Discriminative-Aware Knowledge Preservation Approach for Zero-Shot Sketch-Based Image Retrieval ," Journal of Advances in Information Technology, Vol. 15, No. 3, pp. 364-371, 2024.

Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.