Research map / Vision-language and multimodal / Human and embodied modeling
Large Scale Visual Food Recognition
Weiqing Min, Zhiling Wang, Yuxin Liu, Mengjiang Luo, Liping Kang, Xiaoming Wei, Xiaolin K. Wei, Shuqiang Jiang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase learning stages U from 1 to 3 (ablation) | PRENet(ResNet50) · Food2K | top-1 accuracy (%): 81.45 -> 82.11 -> 83.03 | Improved |
| increase learning stages to U=4 (ablation) | PRENet(ResNet50) · Food2K | top-1 accuracy (%) | Hurt |
| add progressive learning strategy (PL) to simple feature fusion (ablation) | PRENet(ResNet50) · Food2K | top-1 accuracy (%) | Improved |
| add region feature enhancement (RE) on top of PL (ablation) | PRENet(ResNet50) · Food2K | top-1 accuracy (%) | Improved |
| use only cross-entropy loss (alpha=1) instead of adding KL divergence (ablation) | PRENet(ResNet50) · Food2K | top-1 accuracy (%): reduced by 3.18% | Improved |
| use only KL divergence (alpha=0, beta=1) (ablation) | PRENet(ResNet50) · Food2K | top-1 accuracy (%) | Hurt |
| add PRENet to ResNet50 backbone | ResNet50 · Food2K | top-1 accuracy (%): 80.79 -> 83.03 | Improved |
| pre-fine-tune on Food2K before target dataset | VGG16 · Vireo Food-172 | top-1 accuracy (%): 80.41 -> 87.74 | Improved |
| pre-fine-tune on Food2K before target dataset | VGG16 · ETH Food-101 | top-1 accuracy (%): 79.02 -> 80.68 | Improved |
| pre-fine-tune on Food2K instead of ETH Food-101 | Dynamic R-CNN · UNIMIB2016 detection | mAP (%): 69.2 -> 70.6 | Improved |
| fine-tune on ETH Food-101 for metric-learning retrieval | Triplet loss ResNet101 · Vireo Food-172 retrieval | mAP (%): 83.14 -> 77.68 | Hurt |
| fine-tune backbone on Food2K for PSPnet | PSPnet(ResNet50) · UEC-FoodPix Complete | mIoU (%): 70.9 -> 74.5 | Improved |
Closest papers by meaning
- OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation (CVPR 2024 · similarity 0.89)
- OmniFood8K: Single-Image Nutrition Estimation via Hierarchical Frequency-Aligned Fusion (CVPR 2026 · similarity 0.88)
- Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food (CVPR 2021 · similarity 0.88)
- VegFru: A Domain-Specific Dataset for Fine-Grained Visual Categorization (ICCV 2017 · similarity 0.87)
- Exploring Domain Incremental Video Highlights Detection with the LiveFood Benchmark (AAAI 2024 · similarity 0.84)
- Pic2Prep: A Multimodal Conversational Agent for Cooking Assistance (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
