Dataset Groups Activity Stream FSC147 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. BibTex: @dataset{Mingjie_Wang_and_Yande_Li_and_Jun_Zhou_and_Graham_W_Taylor_and_Minglun_Gong_2024, abstract = {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.}, author = {Mingjie Wang and Yande Li and Jun Zhou and Graham W. Taylor and Minglun Gong}, doi = {10.57702/zrr2wibp}, institution = {No Organization}, keyword = {'Class-agnostic counting', 'Convolutional Networks', 'Crowd counting', 'FSC147', 'Object Counting', 'Object detection', 'Spatial Invariance', 'dataset', 'object counting'}, month = {dec}, publisher = {TIB}, title = {FSC147}, url = {https://service.tib.eu/ldmservice/dataset/fsc147}, year = {2024} }
