Summary of Gcam: Gaussian and Causal-attention Model Of Food Fine-grained Recognition, by Guohang Zhuang et al.
GCAM: Gaussian and causal-attention model of food fine-grained recognition
by Guohang Zhuang, Yue Hu, Tianxing Yan, JiaZhan Gao
First submitted to arxiv on: 18 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
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 Gaussian and causal-attention model addresses fine-grained issues in food recognition by extracting features over target regions and enhancing feature mapping capabilities. The model is trained to obtain Gaussian features and then extracts fine-grained features, allowing for more accurate predictions. To mitigate data drift caused by uneven data distributions, a counterfactual reasoning approach is employed, analyzing the impact of learned image attention mechanisms on network predictions. A learnable loss strategy balances training stability across modules, improving overall accuracy. The approach is validated on four relevant datasets, surpassing state-of-the-art methods on three and achieving state-of-the-art performance on one. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way to recognize food by using a special kind of model that focuses on specific parts of the image. This helps to tell similar foods apart. The approach also corrects for unevenness in the data, which makes it more accurate. The model is tested on four different datasets and performs well on most of them. |
Keywords
* Artificial intelligence * Attention
