{"task":"Exemplar-Free Counting","dataset":"FSC147","metric_names":["MAE(test)","RMSE(test)","MAE(val)","RMSE(val)"],"rows":[{"id":52870,"task":"Exemplar-Free Counting","parent_task":"Object Counting","dataset":"FSC147","model_name":"SAVE","metrics":{"MAE(test)":"8.92","MAE(val)":"8.89","RMSE(test)":"80.39","RMSE(val)":"35.83"},"paper_url":"https://www.mdpi.com/2313-433X/11/2/52","paper_title":"SAVE: Self-Attention on Visual Embedding for Zero-Shot Generic Object Counting","paper_date":"2025-02-10","code_links":[{"title":"AhmedZgaren/Save","url":"https://github.com/AhmedZgaren/Save"}],"metrics_order":"[\"MAE(test)\", \"RMSE(test)\", \"MAE(val)\", \"RMSE(val)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52871,"task":"Exemplar-Free Counting","parent_task":"Object Counting","dataset":"FSC147","model_name":"GeCo","metrics":{"MAE(test)":"13.30","MAE(val)":"14.81","RMSE(test)":"108.72","RMSE(val)":"64.95"},"paper_url":"https://arxiv.org/abs/2409.18686v2","paper_title":"A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation","paper_date":"2024-09-27","code_links":[{"title":"jerpelhan/GeCo","url":"https://github.com/jerpelhan/GeCo"}],"metrics_order":"[\"MAE(test)\", \"RMSE(test)\", \"MAE(val)\", \"RMSE(val)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52872,"task":"Exemplar-Free Counting","parent_task":"Object Counting","dataset":"FSC147","model_name":"GCA-SUN","metrics":{"MAE(test)":"14.00","MAE(val)":"16.06","RMSE(test)":"92.19","RMSE(val)":"53.04"},"paper_url":"https://arxiv.org/abs/2409.12249v2","paper_title":"GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting","paper_date":"2024-09-18","code_links":[],"metrics_order":"[\"MAE(test)\", \"RMSE(test)\", \"MAE(val)\", \"RMSE(val)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52873,"task":"Exemplar-Free Counting","parent_task":"Object Counting","dataset":"FSC147","model_name":"CounTR","metrics":{"MAE(test)":"14.71","MAE(val)":"18.07","RMSE(test)":"106.87","RMSE(val)":"71.84"},"paper_url":"https://arxiv.org/abs/2208.13721v3","paper_title":"CounTR: Transformer-based Generalised Visual Counting","paper_date":"2022-08-29","code_links":[{"title":"Verg-Avesta/CounTR","url":"https://github.com/Verg-Avesta/CounTR"}],"metrics_order":"[\"MAE(test)\", \"RMSE(test)\", \"MAE(val)\", \"RMSE(val)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52874,"task":"Exemplar-Free Counting","parent_task":"Object Counting","dataset":"FSC147","model_name":"DAVE","metrics":{"MAE(test)":"15.14","MAE(val)":"15.54","RMSE(test)":"103.49","RMSE(val)":"52.67"},"paper_url":"https://arxiv.org/abs/2404.16622v1","paper_title":"DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting","paper_date":"2024-04-25","code_links":[{"title":"jerpelhan/dave","url":"https://github.com/jerpelhan/dave"}],"metrics_order":"[\"MAE(test)\", \"RMSE(test)\", \"MAE(val)\", \"RMSE(val)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52875,"task":"Exemplar-Free Counting","parent_task":"Object Counting","dataset":"FSC147","model_name":"LOCA","metrics":{"MAE(test)":"16.2","MAE(val)":"17.43","RMSE(test)":"103.96","RMSE(val)":"54.96"},"paper_url":"https://arxiv.org/abs/2211.08217v2","paper_title":"A Low-Shot Object Counting Network With Iterative Prototype Adaptation","paper_date":"2022-11-15","code_links":[{"title":"djukicn/loca","url":"https://github.com/djukicn/loca"}],"metrics_order":"[\"MAE(test)\", \"RMSE(test)\", \"MAE(val)\", \"RMSE(val)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52876,"task":"Exemplar-Free Counting","parent_task":"Object Counting","dataset":"FSC147","model_name":"RCC","metrics":{"MAE(test)":"17.12","MAE(val)":"17.49","RMSE(test)":"104.53","RMSE(val)":"58.81"},"paper_url":"https://arxiv.org/abs/2205.10203v2","paper_title":"Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision","paper_date":"2022-05-20","code_links":[{"title":"SinicaGroup/Class-agnostic-Few-shot-Object-Counting","url":"https://github.com/SinicaGroup/Class-agnostic-Few-shot-Object-Counting"},{"title":"activevisionlab/learningtocountanything","url":"https://github.com/activevisionlab/learningtocountanything"}],"metrics_order":"[\"MAE(test)\", \"RMSE(test)\", \"MAE(val)\", \"RMSE(val)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52877,"task":"Exemplar-Free Counting","parent_task":"Object Counting","dataset":"FSC147","model_name":"RepRPN-Counter","metrics":{"MAE(test)":"26.66","MAE(val)":"29.24","RMSE(test)":"129.11","RMSE(val)":"98.11"},"paper_url":"https://arxiv.org/abs/2201.01488v1","paper_title":"Exemplar-free Class Incremental Learning via Discriminative and Comparable One-class Classifiers","paper_date":"2022-01-05","code_links":[{"title":"SunWenJu123/DCPOC","url":"https://github.com/SunWenJu123/DCPOC"}],"metrics_order":"[\"MAE(test)\", \"RMSE(test)\", \"MAE(val)\", \"RMSE(val)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":52878,"task":"Exemplar-Free Counting","parent_task":"Object Counting","dataset":"FSC147","model_name":"FamNet","metrics":{"MAE(test)":"32.27","MAE(val)":"32.15","RMSE(test)":"131.46","RMSE(val)":"98.75"},"paper_url":"https://arxiv.org/abs/2104.08391v1","paper_title":"Learning To Count Everything","paper_date":"2021-04-16","code_links":[{"title":"cvlab-stonybrook/LearningToCountEverything","url":"https://github.com/cvlab-stonybrook/LearningToCountEverything"}],"metrics_order":"[\"MAE(test)\", \"RMSE(test)\", \"MAE(val)\", \"RMSE(val)\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}