Summary of Semantic Knowledge Distillation For Onboard Satellite Earth Observation Image Classification, by Thanh-dung Le et al.
Semantic Knowledge Distillation for Onboard Satellite Earth Observation Image Classification
by Thanh-Dung Le, Vu Nguyen Ha, Ti Ti Nguyen, Geoffrey Eappen, Prabhu Thiruvasagam, Hong-fu Chou, Duc-Dung Tran, Luis M. Garces-Socarras, Jorge L. Gonzalez-Rios, Juan Carlos Merlano-Duncan, Symeon Chatzinotas
First submitted to arxiv on: 31 Oct 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG); Signal Processing (eess.SP)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This study proposes a novel dynamic weighting knowledge distillation (KD) framework that efficiently classifies Earth observation (EO) images in resource-constrained settings. By utilizing EfficientViT and MobileViT as teacher models, the framework enables lightweight student models to achieve high accuracy, precision, and recall rates. The adaptive weighting mechanism dynamically prioritizes credible sources of knowledge based on each teacher model’s confidence. Notably, ResNet8 delivers significant efficiency gains, reducing parameters by 97.5%, FLOPs by 96.7%, power consumption by 86.2%, and inference speed by 63.5% compared to MobileViT. The framework’s optimization of complexity and resource demands makes ResNet8 an optimal candidate for EO tasks, combining robust performance with feasibility in deployment. This dynamic distillation strategy has the potential to yield high-performing, resource-efficient models tailored for satellite-based EO applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study creates a new way to teach machines how to classify Earth observation images using less resources. They use special teacher models like EfficientViT and MobileViT, which help student models learn quickly and accurately. The students can be as simple as ResNet8 or ResNet16, which are really good at this task. This new method is important because it helps machines do their job with less energy and faster, making it perfect for using on satellites. |
Keywords
» Artificial intelligence » Distillation » Inference » Knowledge distillation » Optimization » Precision » Recall » Teacher model
