HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Object Counting On Carpk

Metrics

MAE
RMSE

Results

Performance results of various models on this benchmark

Model Name
MAE
RMSE
Paper TitleRepository
YOLO (2016)156.0057.55You Only Look Once: Unified, Real-Time Object Detection-
Faster R-CNN (2015)39.8847.67Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks-
One-Look Regression (2016)21.8836.73A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning-
Soft-IoU + EM-Merger unit6.778.52Precise Detection in Densely Packed Scenes-
LPN Counting (2017)22.7634.46Drone-based Object Counting by Spatially Regularized Regional Proposal Network-
HLCNN2.123.02An Accurate Car Counting in Aerial Images Based on Convolutional Neural Networks
VLCounter6.468.68VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting-
CounTR5.757.45CounTR: Transformer-based Generalised Visual Counting-
SAFECount5.337.04Few-shot Object Counting with Similarity-Aware Feature Enhancement-
YOLO9000opt (2017)130.40172.46YOLO9000: Better, Faster, Stronger-
CounTX (uses arbitrary text input to specify object to count, used "the cars" for CARPK)8.1310.87Open-world Text-specified Object Counting-
RetinaNet (2018)16.6222.30Drone-based Object Counting by Spatially Regularized Regional Proposal Network-
RetinaNet (2018)24.58-Focal Loss for Dense Object Detection-
BMNet+5.767.83Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting-
0 of 14 row(s) selected.
Object Counting On Carpk | SOTA | HyperAI