mlsanityData to 7 Oct 2026

Single-Stage Heavy-Tailed Food Classification

arXiv 2307.00182 ↗First posted 1 Jul 2023cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Deep learning based food image classification has enabled more accurate nutrition content analysis for image-based dietary assessment by predicting the types of food in eating occasion images. However, there are two major obstacles to apply food classification in real life applications. First, real life food images are usually heavy-tailed distributed, resulting in severe class-imbalance issue. Second, it is challenging to train a single-stage (i.e. end-to-end) framework under heavy-tailed data distribution, which cause the over-predictions towards head classes with rich instances and under-predictions towards tail classes with rare instance. In this work, we address both issues by introducing a novel single-stage heavy-tailed food classification framework. Our method is evaluated on two heavy-tailed food benchmark datasets, Food101-LT and VFN-LT, and achieves the best performance compared to existing work with over 5% improvements for top-1 accuracy.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 21 of its 29 references that are in the map. First posted on arXiv 1 Jul 2023.

Builds on

21 of 29 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  3. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  4. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  5. 2020Long-tail learning via logit adjustmentcited by 605
  6. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 510
  7. 2021Deep Long-Tailed Learning: A Surveycited by 416
  8. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  9. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  10. 2020The Early Phase of Neural Network Trainingcited by 114
  11. 2022Long-Tailed Recognition via Weight Balancingcited by 107
  12. 2021The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classificationcited by 100
9 more
  1. 2021Influence-Balanced Loss for Imbalanced Visual Classificationcited by 91
  2. 2017Critical Learning Periods in Deep Neural Networkscited by 78
  3. 2021Large Scale Visual Food Recognitioncited by 75
  4. 2017Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networkscited by 58
  5. 2021Online Continual Learning For Visual Food Classificationcited by 39
  6. 2020Visual Aware Hierarchy Based Food Recognitioncited by 38
  7. 2020Multi-Task Image-Based Dietary Assessment for Food Recognition and Portion Size Estimationcited by 26
  8. 2022Long-tailed Food Classificationcited by 19
  9. 2023Online Class-Incremental Learning For Real-World Food Image Classificationcited by 17

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 3; 2025: 3.

10 papers.

  1. 2024MFP3D: Monocular Food Portion Estimation Leveraging 3D Point Cloudscited by 9
  2. 2024DELTA: Decoupling Long-Tailed Online Continual Learningcited by 8
  3. 2023An Improved Encoder-Decoder Framework for Food Energy Estimationcited by 5
  4. 2023Diffusion Model with Clustering-based Conditioning for Food Image Generationcited by 4
  5. 2023Muti-Stage Hierarchical Food Classificationcited by 4
  6. 2023Personalized Food Image Classification: Benchmark Datasets and New Baselinecited by 4
  7. 2024Automatic Recognition of Food Ingestion Environment from the AIM-2 Wearable Sensorcited by 4
  8. 2025Comprehensive Evaluation of Large Multimodal Models for Nutrition Analysis: A New Benchmark Enriched with Contextual Metadatacited by 3
  9. 2025Synthetic Data Augmentation using Pre-trained Diffusion Models for Long-tailed Food Image Classificationcited by 2
  10. 2025Personalized Class Incremental Context-Aware Food Classification for Food Intake Monitoring Systemscited by 0