CUB-200-2011

The 'CUB-200-2011' dataset is a benchmark that contains images of 200 bird species, annotated with attributes, and is used to evaluate visual recognition and retrieval systems.

Papers using CUB-200-2011 (8)

Subtoken Vision Transformer for Fine-grained Recognition2026PAND: Prompt-Aware Neighborhood Distillation for Lightweight Fine-Grained Visual Classification2026TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglement2026DSeq-JEPA: Discriminative Sequential Joint-Embedding Predictive Architecture2025Training Vision Transformers for Image Retrieval2021 · 122 citesConstrained Sampling for Class-Agnostic Weakly Supervised Object Localization2022 · 5 citesObjects as context for detecting their semantic parts2017 · 1 citesDual Progressive Transformations for Weakly Supervised Semantic Segmentation2022