9 datasets found

The FSCD-LVIS dataset is used to evaluate the proposed method.

Class-agnostic object counting aims to count all objects in an image with respect to example boxes or class names, a.k.a few-shot and zero-shot counting.

A dataset for text-to-image generation with accurate object count. The dataset consists of 200 prompts with various classes, numbers, and scenes.

The CARPK dataset is a large-scale aerial dataset for counting cars in parking lots. It contains images with a top-down view covering 4 different parking lots.

Flickr30k-Counting is a benchmark for object counting.

Object counting in images

Class-Agnostic Counting (CAC) dataset, includes 6,135 images across 147 categories, divided into 3,659 training, 1,286 validation, and 1,190 test images.

The FSC147 dataset is a large-scale dataset for evaluating class-agnostic counting (CAC) models. It contains 6,135 natural images of 147 object categories.

The COCO-QA-OBJ dataset is used for object counting task. It consists of 123,287 images and 78,736 train and 38,948 test questions.