Object Counting on CARPK

Metric: MAE (lower is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	MAE▲	Extra Data	Paper	Date↕	Code
1	HLCNN	2.12	No	-	-	Code
2	CLIP-LOCAR	4.01	No	Car Object Counting and Position Estimation via ...	2025-07-11	Code
3	SAFECount	5.33	No	Few-shot Object Counting with Similarity-Aware F...	2022-01-22	Code
4	CounTR	5.75	No	CounTR: Transformer-based Generalised Visual Cou...	2022-08-29	Code
5	BMNet+	5.76	No	Represent, Compare, and Learn: A Similarity-Awar...	2022-03-16	Code
6	VLCounter	6.46	No	VLCounter: Text-aware Visual Representation for ...	2023-12-27	Code
7	Soft-IoU + EM-Merger unit	6.77	No	Precise Detection in Densely Packed Scenes	2019-04-01	Code
8	CounTX (uses arbitrary text input to specify object to count, used "the cars" for CARPK)	8.13	No	Open-world Text-specified Object Counting	2023-06-02	Code
9	RetinaNet (2018)	16.62	No	Drone-based Object Counting by Spatially Regular...	2017-07-19	-
10	One-Look Regression (2016)	21.88	No	A Large Contextual Dataset for Classification, D...	2016-09-14	-
11	LPN Counting (2017)	22.76	No	Drone-based Object Counting by Spatially Regular...	2017-07-19	-
12	RetinaNet (2018)	24.58	No	Focal Loss for Dense Object Detection	2017-08-07	Code
13	Faster R-CNN (2015)	39.88	No	Faster R-CNN: Towards Real-Time Object Detection...	2015-06-04	Code
14	YOLO9000opt (2017)	130.4	No	YOLO9000: Better, Faster, Stronger	2016-12-25	Code
15	YOLO (2016)	156	No	You Only Look Once: Unified, Real-Time Object De...	2015-06-08	Code

#1HLCNN
2.12
MAE
No paperCode
#2CLIP-LOCARSOTA
4.01
MAE· 2025-07-11
Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework Code
#3SAFECountSOTA
5.33
MAE· 2022-01-22
Few-shot Object Counting with Similarity-Aware Feature Enhancement Code
#4CounTR
5.75
MAE· 2022-08-29
CounTR: Transformer-based Generalised Visual Counting Code
#5BMNet+
5.76
MAE· 2022-03-16
Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting Code
#6VLCounter
6.46
MAE· 2023-12-27
VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting Code
#7Soft-IoU + EM-Merger unitSOTA
6.77
MAE· 2019-04-01
Precise Detection in Densely Packed Scenes Code
#8CounTX (uses arbitrary text input to specify object to count, used "the cars" for CARPK)
8.13
MAE· 2023-06-02
Open-world Text-specified Object Counting Code
#9RetinaNet (2018)SOTA
16.62
MAE· 2017-07-19
Drone-based Object Counting by Spatially Regularized Regional Proposal Network
#10One-Look Regression (2016)SOTA
21.88
MAE· 2016-09-14
A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning
#11LPN Counting (2017)
22.76
MAE· 2017-07-19
Drone-based Object Counting by Spatially Regularized Regional Proposal Network
#12RetinaNet (2018)
24.58
MAE· 2017-08-07
Focal Loss for Dense Object Detection Code
#13Faster R-CNN (2015)SOTA
39.88
MAE· 2015-06-04
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Code
#14YOLO9000opt (2017)
130.4
MAE· 2016-12-25
YOLO9000: Better, Faster, Stronger Code
#15YOLO (2016)
156
MAE· 2015-06-08
You Only Look Once: Unified, Real-Time Object Detection Code