Object Counting
60 papers with code • 10 benchmarks • 23 datasets
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
Benchmarks
These leaderboards are used to track progress in Object Counting
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Object Counting models and implementations
MS COCO
PASCAL VOC
PASCAL VOC 2007
FSOD
CARPK
FSC147
COWC
TallyQA
AGAR
Most implemented papers
Object Counting and Instance Segmentation with Image-level Supervision
GuoleiSun/CountSeg
•
•
CVPR 2019
Moreover, our approach improves state-of-the-art image-level supervised instance segmentation with a relative gain of 17. 8% in terms of average best overlap, on the PASCAL VOC 2012 dataset.
Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning
To address this dilemma, we further propose an uncertainty-aware cross-modality vehicle detection (UA-CMDet) framework to extract complementary information from cross-modal images, which can significantly improve the detection performance in low light conditions.
Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting
Pongpisit-Thanasutives/Variations-of-SFANet-for-Crowd-Counting
•
•
Inspired by SFANet, the first model, which is named M-SFANet, is attached with atrous spatial pyramid pooling (ASPP) and context-aware module (CAN).
Unsupervised Domain Adaptation For Plant Organ Counting
p2irc/UDA4POC
•
•
Supervised learning is often used to count objects in images, but for counting small, densely located objects, the required image annotations are burdensome to collect.
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models
In this work, we investigate the visual reasoning capabilities and social biases of different text-to-image models, covering both multimodal transformer language models and diffusion models.
Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision
activevisionlab/learningtocountanything
•
•
Specifically, we demonstrate that regression from vision transformer features without point-level supervision or reference images is superior to other reference-less methods and is competitive with methods that use reference images.
Counting Everyday Objects in Everyday Scenes
prithv1/cvpr2017_counting
•
•
CVPR 2017
In this work, we build dedicated models for counting designed to tackle the large variance in counts, appearances, and scales of objects found in natural scenes.
TallyQA: Answering Complex Counting Questions
Most counting questions in visual question answering (VQA) datasets are simple and require no more than object detection.
Class-Agnostic Counting
erikalu/class-agnostic-counting
•
•
The model achieves competitive performance on cell and crowd counting datasets, and surpasses the state-of-the-art on the car dataset using only three training images.
Towards Partial Supervision for Generic Object Counting in Natural Scenes
Our RLC framework further reduces the annotation cost arising from large numbers of object categories in a dataset by only using lower-count supervision for a subset of categories and class-labels for the remaining ones.
