SOTAVerified

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

Showing 150 of 158 papers

TitleStatusHype
VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement LearningCode4
CountGD: Multi-Modal Open-World CountingCode3
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation ModelsCode3
RemoteCLIP: A Vision Language Foundation Model for Remote SensingCode2
RS-Agent: Automating Remote Sensing Tasks through Intelligent AgentCode2
InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object RecognitionCode2
CNN-based Density Estimation and Crowd Counting: A SurveyCode2
Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and AnalysisCode2
Self-Supervised Learning from Images with a Joint-Embedding Predictive ArchitectureCode2
Roboflow 100: A Rich, Multi-Domain Object Detection BenchmarkCode2
Point Segment and Count: A Generalized Framework for Object CountingCode2
DAVE -- A Detect-and-Verify Paradigm for Low-Shot CountingCode2
A Novel Unified Architecture for Low-Shot Counting by Detection and SegmentationCode2
GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial TasksCode2
Semantic Generative Augmentations for Few-Shot CountingCode1
Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic CountingCode1
Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel SynthesisCode1
Rethinking Spatial Invariance of Convolutional Networks for Object CountingCode1
SAVE: Self-Attention on Visual Embedding for Zero-Shot Generic Object CountingCode1
STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance LearningCode1
Point, Segment and Count: A Generalized Framework for Object CountingCode1
EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question AnsweringCode1
Class-agnostic-Few-shot-Object-CountingCode1
Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic CountingCode1
Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic CountingCode1
Learning to Count Anything: Reference-less Class-agnostic Counting with Weak SupervisionCode1
A Low-Shot Object Counting Network With Iterative Prototype AdaptationCode1
IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance SamplingCode1
Learning To Count EverythingCode1
Learning to Count without AnnotationsCode1
PSGCNet: A Pyramidal Scale and Global Context Guided Network for Dense Object Counting in Remote Sensing ImagesCode1
Can SAM Count Anything? An Empirical Study on SAM CountingCode1
Counting with Adaptive Auxiliary LearningCode1
Heatmap-based Object Detection and Tracking with a Fully Convolutional Neural NetworkCode1
Image Augmentation for Multitask Few-Shot Learning: Agricultural Domain Use-CaseCode1
Few-shot Object Counting and DetectionCode1
CounTR: Transformer-based Generalised Visual CountingCode1
Automating cell counting in fluorescent microscopy through deep learning with c-ResUnetCode1
Few-shot Object LocalizationCode1
Counting from Sky: A Large-scale Dataset for Remote Sensing Object Counting and A Benchmark MethodCode1
An Accurate Car Counting in Aerial Images Based on Convolutional Neural NetworksCode1
Few-shot Object Counting with Similarity-Aware Feature EnhancementCode1
Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware LearningCode1
From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object CountingCode1
NWPU-MOC: A Benchmark for Fine-grained Multi-category Object Counting in Aerial ImagesCode1
Open-world Text-specified Object CountingCode1
RGB-D Indiscernible Object Counting in Underwater ScenesCode1
Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd CountingCode1
CLIP-Count: Towards Text-Guided Zero-Shot Object CountingCode1
Real Time Pear Fruit Detection and Counting Using YOLOv4 Models and Deep SORTCode1
Show:102550
← PrevPage 1 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FamNetMAE(test)22.08Unverified
2Omnicount (Open vocabulary, multi-label, without training)MAE(test)18.63Unverified
3RCCMAE(test)17.12Unverified
4Counting-DETRMAE(test)16.79Unverified
5CounTX (uses text descriptions instead of visual exemplars)MAE(test)15.88Unverified
6LaoNetMAE(test)15.78Unverified
7BMNet+MAE(test)14.62Unverified
8SAFECountMAE(test)14.32Unverified
9GCA-SUNMAE(test)14Unverified
10SPDCNMAE(test)13.51Unverified
#ModelMetricClaimedVerifiedStatus
1YOLO (2016)MAE156Unverified
2YOLO9000opt (2017)MAE130.4Unverified
3Faster R-CNN (2015)MAE39.88Unverified
4RetinaNet (2018)MAE24.58Unverified
5LPN Counting (2017)MAE22.76Unverified
6One-Look Regression (2016)MAE21.88Unverified
7RetinaNet (2018)MAE16.62Unverified
8CounTX (uses arbitrary text input to specify object to count, used "the cars" for CARPK)MAE8.13Unverified
9Soft-IoU + EM-Merger unitMAE6.77Unverified
10VLCounterMAE6.46Unverified
#ModelMetricClaimedVerifiedStatus
1Fast-RCNNm-reIRMSE-nz0.85Unverified
2glance-noft-2Lm-reIRMSE-nz0.73Unverified
3LC-PSPNetm-reIRMSE-nz0.7Unverified
4Seq-sub-ft-3x3m-reIRMSE-nz0.68Unverified
5ensm-reIRMSE-nz0.65Unverified
6Supervised Density Mapm-reIRMSE-nz0.61Unverified
7LC-ResFCNm-reIRMSE-nz0.61Unverified
8OmnicountmRMSE0Unverified
#ModelMetricClaimedVerifiedStatus
1Aso-sub-ft-3x3m-reIRMSE0.24Unverified
2glance-ft-2Lm-reIRMSE0.23Unverified
3Fast-RCNNm-reIRMSE0.2Unverified
4LC-ResFCNm-reIRMSE0.19Unverified
5Seq-sub-ft-3x3m-reIRMSE0.18Unverified
6Supervised Density Mapm-reIRMSE0.18Unverified
7ensm-reIRMSE0.18Unverified
#ModelMetricClaimedVerifiedStatus
1SMoLA-PaLI-X SpecialistAccuracy77.1Unverified
2PaLI-X-VPDAccuracy76.6Unverified
3SMoLA-PaLI-X Generalist (0 shot)Accuracy70.7Unverified
4MoVie-ResNeXtAccuracy56.8Unverified
5RCNAccuracy56.2Unverified
6MoVieAccuracy54.1Unverified
#ModelMetricClaimedVerifiedStatus
1SMoLA-PaLI-X SpecialistAccuracy86.3Unverified
2PaLI-X-VPDAccuracy86.2Unverified
3SMoLA-PaLI-X Generalist (0 shot)Accuracy83.3Unverified
4MoVie-ResNeXtAccuracy74.9Unverified
5RCNAccuracy71.8Unverified
6MoVieAccuracy70.8Unverified
#ModelMetricClaimedVerifiedStatus
1MoVie-ResNeXtAccuracy64Unverified
2MoVieAccuracy61.2Unverified
3RCNAccuracy60.3Unverified
#ModelMetricClaimedVerifiedStatus
1CEOESmRMSE0.42Unverified
2ILCmRMSE0.29Unverified
3TFOCmRMSE0.01Unverified
#ModelMetricClaimedVerifiedStatus
1OmnicountmRMSE0Unverified
#ModelMetricClaimedVerifiedStatus
1GauNet (ResNet-50)MAE2.1Unverified