Food-101

Introduced by Lukas Bossard et al. in Food-101 - Mining Discriminative Components with Random Forests

The Food-101 dataset consists of 101 food categories with 750 training and 250 test images per category, making a total of 101k images. The labels for the test images have been manually cleaned, while the training set contains some noise.

Source: Combining Weakly and Webly Supervised Learning for Classifying Food Images

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Fine-Grained Image Classification	Food-101	CAP
Prompt Engineering	Food-101	PromptKD
Image Classification	food101	swin-finetuned-food101-e3
Image Classification	Food-101	Bamboo
Zero-Shot Transfer Image Classification	Food-101	MAWS
Neural Architecture Search	Food-101	NAT-M3
Multi-Modal Document Classification	Food-101	Early Fusion
Multimodal Text and Image Classification	Food-101	Late Fusion
Image Compression	Food-101	Lossyless Compressor
Few-Shot Learning	food101	Variational Prompt Tuning
Document Text Classification	Food-101	Bert