BenchmarkCOCO
MSCOCO
A large-scale dataset for object detection, segmentation and image captioning, commonly used for evaluating multimodal vision-language tasks.
Timeline (last 90 days)
Oct 16
The MYOPIA benchmark contains four decision trees generated by LLMs and refined manually, corresponding to the GTSRB, MNIST, CIFAR-10, and MSCOCO datasets respectively.
Unverified50%