Title: Learning Beyond Deep Learning (LBDL)
Description:
There has been a rapid development of artificial intelligence and machine learning technologies in the last decade. Although deep learning networks have significantly impacted various application domains such as computer vision, natural language processing, autonomous driving, robotics navigation, etc., they have several limitations. They are mathematically intractable, vulnerable to adversarial attacks, and demand a lot of training data. Furthermore, their training is computationally intensive, and their large model sizes make deploying mobile and edge devices a significant challenge. Developing new machine learning paradigms beyond deep learning is highly desirable. We intend to use this workshop to attract researchers of common interests and generate momentum for future breakthroughs. One or more characteristics will feature the new learning paradigm: interpretability, smaller model sizes, lower computational complexities, and high performance.
This workshop and another workshop titled “Transparent Image Processing (TIP)” of ICIP 2025 are sister workshops. LBDL focuses on learning-based models that deviate from deep learning in parts or whole. In contrast, TIP covers learning- and non-learning-based image processing algorithms emphasizing algorithmic transparency.
Submission Guidelines:
Please submit your work using the following link:
https://cmsworkshops.com/ICIP2025/papers/submission.asp?Type=WS&ID=10
All invited and regular papers will follow the 6-page requirement of the main ICIP conference, and a technical program committee of the Workshop will review them.
| Satellite Workshop Paper Submission Deadline | 4 June 2025 |
| Satellite Workshop Paper Acceptance Notification | 2 July 2025 |
| Satellite Workshop Final Paper Submission Deadline | 9 July 2025 |
| Satellite Workshop Author Registration Deadline | 16 July 2025 |
Organizers:
- C.-C. Jay Kuo, University of Southern California, USA, email: jckuo@usc.edu
- Ling Guan, Toronto Metropolitan Univ/Ryerson Univ, Canada, email: lguan@ee.ryerson.ca
Technical Program Committee Members:
- Lei Gao, Toronto Metropolitan University, Canada
- Dongwoo Kang, Hongik University, Korea
- Jewon Kang, Ewha Womans University, Korea
- Ming-Sui Lee, National Taiwan University, Taiwan
- Jianquan Liu, NEC Corporation, Japan
- Xiaofeng Liu, Yale University, USA
- Bojan Mihaljevic, Universidad Politécnica de Madrid, Spain
- Paisarn Muneesawang, Mahidol University, Thailand
- Witold Pedrycz, University of Alberta, Canada
- Simon Pun, Chinese University of Hong Kong (Shenzhen), China
- Yuzhuo Ren, Nvidia, USA
- Xinchao Wang, National University of Singapore, Singapore
- Harry Yang, Hong Kong University of Science and Technology, Hong Kong
- Niclas Zeller, Hochschule Karlsruhe University of Applied Sciences, Germany
Program of the LBDL Satellite Workshop:
Satellite Workshop WS-10: Learning Beyond Deep Learning (LBDL)
Date: September 18, 2025 (Thursday)
Location: Dena’ina: Kahtnu 2
Section I: Chair: C.-C. Jay Kuo, University of Southern California
8:30-8:50 [P2892]
Antoni Buades, Universitat Illes Balears; Pau Céspedes, Universitat Illes Balears; Jose-
Luis Lisani, Universitat Illes Balears; Marco Sánchez-Beeckman, Universitat Illes
Balears: “Lightweight Video Denoising with Hybrid Approach”
8:50-9:10 [P2902]
Changchang Sun, University of Illinois Chicago; Jialie Shen, University of London;
Gaowen Liu, Cisco Research; Aihua Zheng, Anhui University; Yan Yan, University of
Illinois Chicago;
“Tie-breaking Conflict-ease Cross-modal Hashing”
9:10-9:30 [P3078]
Lei Gao, Toronto Metropolitan University; Kai Liu, Toronto Metropolitan University;
Zheng Guo, Toronto Metropolitan University; Ling Guan, Toronto Metropolitan University
“Multi-view Analysis: Back to the Classic with a NN Twist”
9:30-10 Coffee Break
Section II: Chair: Ling Guan
10-10:20 [P2983]
Haiyi Li, University of Southern California; Qi Cao, University of Southern California; C.-
C. Jay Kuo, University of Southern California;
“MXB: Multi-stage XGboost for Efficient Tree-based Gradient Boosting”
10:20-10:40 [P2987]
Rohit Venkata Sai Dulam, University of Delaware; Chandra Kambhamettu, University of
Delaware;
“USODFUSENET – A Novel Underwater Salient Object Detection Model”
10:40-11 [P3020]
Viet Ho Tam Thuc Do, York University; Parham Eftekhar, York University; Gene Cheung,
York University;
“Lightweight Transformer for Image Interpolation via Unrolling of Multiple Learned Graph
Laplacian Regularizers”
11-11:20 [P3031]
Chiao-Yin Hsu, National Taiwan University; Ming-Sui Lee, National Taiwan University;
“FREEDRAPE: Free-form Garment Transfer via Pose-Aware Bidirectional Warping”
11:20-11:40 [P2910]
Yutaro Hiraoka, the Japan Research Institute; Kazuya Okamura, University of Tsukuba;
Kota Suto, University of Tsukuba; Kazuhiro Fukui, University of Tsukuba;
“Attention Mechanism in Randomized Time Warping”
11:40-12 [P3092]
Hurriyatul Fitriyah, University of South Australia; Paisarn Muneesawang, Mahidol
University; Ivan Lee, University of South Australia
“Few-view X-ray CT Segmentation of Thin Tubular Structures”