CUB-200

The CUB-200 dataset is a benchmark that contains images of 200 bird species and is used to evaluate fine-grained recognition tasks in computer vision.

Papers using CUB-200 (5)

Leveraging Vision-language Models As Weak Annotators In Active Learning2026BareBones: Benchmarking Zero-Shot Geometric Comprehension in VLMs2026PAND: Prompt-Aware Neighborhood Distillation for Lightweight Fine-Grained Visual Classification2026Preserving Cross-Modal Consistency for CLIP-based Class-Incremental Learning2025Fine-grained Cross-modal Fusion based Refinement for Text-to-Image Synthesis2023