Object Counting

The goal of Object Counting task is to count the number of object instances in a single image or video sequence. It has many real-world applications such as traffic flow monitoring, crowdedness estimation, and product counting.

Source: Learning to Count Objects with Few Exemplar Annotations

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 76–100 of 158 papers

Title	Date	Tasks	Status	Hype
RGB-D Indiscernible Object Counting in Underwater Scenes	Apr 23, 2023	BenchmarkingDepth Estimation	CodeCode Available	1
Can SAM Count Anything? An Empirical Study on SAM Counting	Apr 21, 2023	Object Counting	CodeCode Available	1
Density Map Distillation for Incremental Object Counting	Apr 11, 2023	Exemplar-FreeIncremental Learning	—Unverified	0
TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering	Mar 21, 2023	4kImage Generation	CodeCode Available	1
Deep-Learning-based Counting Methods, Datasets, and Applications in Agriculture -- A Review	Mar 5, 2023	Deep LearningObject Counting	—Unverified	0
Zero-shot Object Counting	Mar 3, 2023	ObjectObject Counting	CodeCode Available	1
Teaching CLIP to Count to Ten	Feb 23, 2023	counterfactualImage Generation	CodeCode Available	1
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture	Jan 19, 2023	Depth EstimationDepth Prediction	CodeCode Available	2
A Unified Object Counting Network with Object Occupation Prior	Dec 29, 2022	Crowd CountingKnowledge Distillation	CodeCode Available	0
Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting	Dec 21, 2022	Object Counting	CodeCode Available	1
Fast-moving object counting with an event camera	Dec 16, 2022	ObjectObject Counting	—Unverified	0
Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark	Nov 24, 2022	2D Object DetectionImage Retrieval	CodeCode Available	2
A Low-Shot Object Counting Network With Iterative Prototype Adaptation	Nov 15, 2022	Exemplar-Free CountingObject	CodeCode Available	1
CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection	Sep 13, 2022	3D Object DetectionObject	—Unverified	0
CounTR: Transformer-based Generalised Visual Counting	Aug 29, 2022	Exemplar-Free CountingObject Counting	CodeCode Available	1
Few-shot Object Counting and Detection	Jul 22, 2022	Few-shot Object Counting and DetectionFew-Shot Object Detection	CodeCode Available	1
Rethinking Spatial Invariance of Convolutional Networks for Object Counting	Jun 10, 2022	Crowd CountingObject	CodeCode Available	1
Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision	May 20, 2022	Exemplar-Free CountingObject Counting	CodeCode Available	1
An application of Pixel Interval Down-sampling (PID) for dense tiny microorganism counting on environmental microorganism images	Apr 4, 2022	DecoderObject Counting	—Unverified	0
Improved Counting and Localization from Density Maps for Object Detection in 2D and 3D Microscopy Imaging	Mar 29, 2022	ObjectObject Counting	—Unverified	0
Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting	Mar 16, 2022	Object Counting	CodeCode Available	1
Counting with Adaptive Auxiliary Learning	Mar 8, 2022	Auxiliary LearningObject Counting	CodeCode Available	1
Domain Randomization for Object Counting	Feb 17, 2022	ObjectObject Counting	CodeCode Available	0
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models	Feb 8, 2022	DiagnosticImage Captioning	CodeCode Available	3
Few-shot Object Counting with Similarity-Aware Feature Enhancement	Jan 22, 2022	Crowd CountingObject Counting	CodeCode Available	1

Show:10 25 50

← PrevPage 4 of 7Next →

All datasets FSC147 CARPK Pascal VOC 2007 count-test COCO count-test TallyQA-Complex TallyQA-Simple HowMany-QA PASCAL VOC Omnicount-191 TRANCOS

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	FamNet	MAE(test)	22.08	—	Unverified
2	Omnicount (Open vocabulary, multi-label, without training)	MAE(test)	18.63	—	Unverified
3	RCC	MAE(test)	17.12	—	Unverified
4	Counting-DETR	MAE(test)	16.79	—	Unverified
5	CounTX (uses text descriptions instead of visual exemplars)	MAE(test)	15.88	—	Unverified
6	LaoNet	MAE(test)	15.78	—	Unverified
7	BMNet+	MAE(test)	14.62	—	Unverified
8	SAFECount	MAE(test)	14.32	—	Unverified
9	GCA-SUN	MAE(test)	14	—	Unverified
10	SPDCN	MAE(test)	13.51	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	YOLO (2016)	MAE	156	—	Unverified
2	YOLO9000opt (2017)	MAE	130.4	—	Unverified
3	Faster R-CNN (2015)	MAE	39.88	—	Unverified
4	RetinaNet (2018)	MAE	24.58	—	Unverified
5	LPN Counting (2017)	MAE	22.76	—	Unverified
6	One-Look Regression (2016)	MAE	21.88	—	Unverified
7	RetinaNet (2018)	MAE	16.62	—	Unverified
8	CounTX (uses arbitrary text input to specify object to count, used "the cars" for CARPK)	MAE	8.13	—	Unverified
9	Soft-IoU + EM-Merger unit	MAE	6.77	—	Unverified
10	VLCounter	MAE	6.46	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Fast-RCNN	m-reIRMSE-nz	0.85	—	Unverified
2	glance-noft-2L	m-reIRMSE-nz	0.73	—	Unverified
3	LC-PSPNet	m-reIRMSE-nz	0.7	—	Unverified
4	Seq-sub-ft-3x3	m-reIRMSE-nz	0.68	—	Unverified
5	ens	m-reIRMSE-nz	0.65	—	Unverified
6	LC-ResFCN	m-reIRMSE-nz	0.61	—	Unverified
7	Supervised Density Map	m-reIRMSE-nz	0.61	—	Unverified
8	Omnicount	mRMSE	0	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Aso-sub-ft-3x3	m-reIRMSE	0.24	—	Unverified
2	glance-ft-2L	m-reIRMSE	0.23	—	Unverified
3	Fast-RCNN	m-reIRMSE	0.2	—	Unverified
4	LC-ResFCN	m-reIRMSE	0.19	—	Unverified
5	Supervised Density Map	m-reIRMSE	0.18	—	Unverified
6	ens	m-reIRMSE	0.18	—	Unverified
7	Seq-sub-ft-3x3	m-reIRMSE	0.18	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SMoLA-PaLI-X Specialist	Accuracy	77.1	—	Unverified
2	PaLI-X-VPD	Accuracy	76.6	—	Unverified
3	SMoLA-PaLI-X Generalist (0 shot)	Accuracy	70.7	—	Unverified
4	MoVie-ResNeXt	Accuracy	56.8	—	Unverified
5	RCN	Accuracy	56.2	—	Unverified
6	MoVie	Accuracy	54.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SMoLA-PaLI-X Specialist	Accuracy	86.3	—	Unverified
2	PaLI-X-VPD	Accuracy	86.2	—	Unverified
3	SMoLA-PaLI-X Generalist (0 shot)	Accuracy	83.3	—	Unverified
4	MoVie-ResNeXt	Accuracy	74.9	—	Unverified
5	RCN	Accuracy	71.8	—	Unverified
6	MoVie	Accuracy	70.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MoVie-ResNeXt	Accuracy	64	—	Unverified
2	MoVie	Accuracy	61.2	—	Unverified
3	RCN	Accuracy	60.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CEOES	mRMSE	0.42	—	Unverified
2	ILC	mRMSE	0.29	—	Unverified
3	TFOC	mRMSE	0.01	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Omnicount	mRMSE	0	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GauNet (ResNet-50)	MAE	2.1	—	Unverified