Work

Semi-PKD: Semi-supervised Pseudoknowledge Distillation for saliency prediction

Year: 2024

Type: article

Abstract: In saliency prediction, Knowledge Distillation (KD) is leveraged to improve the predictive performance of compact Student Networks. However, the challenge is searching for an optimal teacher–student pair while handling the unavailability of large-scale annotations in the Pseudoknowledge Distillation (PKD). To overcome this challenge, a semi-supervised method is proposed; Semi-PKD. This method involves pseudo-label generation on unlabeled data by a Teacher Network trained using the exponential moving average KD (EMA-KD) method. The EMA-KD method utilizes only the Student Network by acquiring self-knowledge, solving the problem of optimal teacher–student pair selection. Semi-PKD outperforms other state-of-the-art saliency prediction models across various evaluation metrics. The code is available at https://github.com/chakkritte/Semi-PKD .

Source: ICT Express

DOI: 10.1016/j.icte.2024.11.004

Authors: Chakkrit Termritthikun, Ayaz Umer, Suwichaya Suwanwimolkul, Ivan Lee

Institutions: Naresuan University, Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Chulalongkorn University, University of South Australia

Language: English

Topic: Visual Attention and Saliency Detection

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Quality education

Open Access status: gold

Estimated APC paid: $1,500