Summary of From Canteen Food to Daily Meals: Generalizing Food Recognition to More Practical Scenarios, by Guoshan Liu et al.
From Canteen Food to Daily Meals: Generalizing Food Recognition to More Practical Scenarios
by Guoshan Liu, Yang Jiao, Jingjing Chen, Bin Zhu, Yu-Gang Jiang
First submitted to arxiv on: 12 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 The proposed paper addresses the challenge of recognizing food categories in daily life scenarios, building upon existing research and benchmarks in the field. The authors introduce two new datasets, DailyFood-172 and DailyFood-16, designed to capture food images from everyday meals, which are used to evaluate the transferability of approaches from well-curated food image domains to real-life applications. A simple yet effective baseline method, Multi-Cluster Reference Learning (MCRL), is also proposed to tackle the domain gap between these datasets. MCRL is motivated by the observation that food images in daily-life scenarios exhibit greater intra-class appearance variance compared with those in well-curated benchmarks. The authors hope their new benchmarks will inspire the community to explore the transferability of food recognition models trained on well-curated datasets toward practical real-life applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper presents a solution for recognizing food categories in everyday life. It’s about creating better ways to identify different types of food in daily meals, using images from real-life scenarios. The researchers introduce two new sets of images, called DailyFood-172 and DailyFood-16, which are designed to help models trained on well-curated datasets work better in real-life situations. They also propose a simple method, called Multi-Cluster Reference Learning (MCRL), that can be used with existing approaches to improve performance. The goal is to make food recognition more practical for everyday life. |
Keywords
» Artificial intelligence » Transferability
