CUB-200-2011 (Caltech-UCSD Birds-200-2011)

Introduced by Wah et al. in The Caltech-UCSD Birds-200-2011 Dataset

The Caltech-UCSD Birds-200-2011 (CUB-200-2011) dataset is the most widely-used dataset for fine-grained visual categorization task. It contains 11,788 images of 200 subcategories belonging to birds, 5,994 for training and 5,794 for testing. Each image has detailed annotations: 1 subcategory label, 15 part locations, 312 binary attributes and 1 bounding box. The textual information comes from Reed et al.. They expand the CUB-200-2011 dataset by collecting fine-grained natural language descriptions. Ten single-sentence descriptions are collected for each image. The natural language descriptions are collected through the Amazon Mechanical Turk (AMT) platform, and are required at least 10 words, without any information of subcategories and actions.

Source: Fine-grained Visual-textual Representation Learning

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Fine-Grained Image Classification	CUB-200-2011	HERBS
Few-Shot Image Classification	CUB 200 5-way 1-shot	PT+MAP+SF+SOT
Few-Shot Image Classification	CUB 200 5-way 5-shot	CAML [Laion-2b]
Metric Learning	CUB-200-2011	Unicom+ViT-L@336px
Fine-Grained Image Classification	CUB-200-2011	HERBS
Text-to-Image Generation	CUB	TLDM
Zero-Shot Learning	CUB-200-2011	DUET
Weakly-Supervised Object Localization	CUB-200-2011	DiPS
Cross-Domain Few-Shot	CUB	StyleAdv-FT
Image Retrieval	CUB-200-2011	CGD
Point-interactive Image Colorization	CUB-200-2011	iColoriT
Unsupervised Keypoint Estimation	CUB	unsup-parts
Few-Shot Image Classification	CUB-200-2011 - 0-Shot	Word CNN-RNN
Generalized Few-Shot Learning	CUB	MVCN
Long-tail learning with class descriptors	CUB-LT	DRAGON + Bal'Loss
Few-Shot Image Classification	CUB 200 50-way (0-shot)	DS-SJE Reed et al.
Image Clustering	CUB Birds	FineGAN
Small Data Image Classification	CUB-200-2011, 30 samples per class	GLICO
Image Classification	CUB	Entropy-based Logic Explained Network
Image Generation	CUB 128 x 128	Projected GAN
Few-Shot Image Classification	CUB-200 - 0-Shot Learning	SJE
Graph Matching	CUB	URL
Few-Shot Class-Incremental Learning	CUB-200-2011	SV-T
Image Classification	CUB-200-2011	Sparse-CBM
Fine-Grained Image Recognition	CUB Birds	HOI-Net
Weakly-Supervised Object Localization	CUB-200-2011	Stable diffusion
Interpretable Machine Learning	CUB-200-2011	Q-SENN
Image Classification	Imbalanced CUB-200-2011	Multi-task
Generalized Zero-Shot Learning	CUB-200-2011	SPOT
Fine-Grained Image Recognition	CUB-200-2011	PIM
Metric Learning	CUB-200-2011	Hyp-DINO
Semantic correspondence	CUB-200-2011	LDMCorrespondences
Fine-Grained Image Classification	Imbalanced CUB-200-2011	PC-Softmax
Zero-Shot Learning	CUB-200 - 0-Shot Learning	zsl_ADA
Small Data Image Classification	CUB-200-2011, 5 samples per class	GLICO
Few-Shot Image Classification	CUB-200-2011 5-way (1-shot)	MATANet
Few-Shot Image Classification	CUB-200-2011 5-way (5-shot)	MATANet
Multimodal Deep Learning	CUB-200-2011	Two Branch Network
Document Text Classification	CUB-200-2011	Bert
Multimodal Text and Image Classification	CUB-200-2011	Two Branch Network
Multi-Modal Document Classification	CUB-200-2011	Two Branch Network
Weakly-Supervised Object Localization	CUB	TokenCut
Single-View 3D Reconstruction	CUB-200-2011	3D Magic Mirror
Image Clustering	CUB-200-2011	MES-Loss