Computer Vision
 
Edit

Object Detection

3725 papers with code • 91 benchmarks • 262 datasets

Object Detection is a computer vision task in which the goal is to detect and locate objects of interest in an image or video. The task involves identifying the position and boundaries of objects in an image, and classifying the objects into different categories. It forms a crucial part of vision recognition, alongside image classification and retrieval.

The state-of-the-art methods can be categorized into two main types: one-stage methods and two stage-methods:

  • One-stage methods prioritize inference speed, and example models include YOLO, SSD and RetinaNet.

  • Two-stage methods prioritize detection accuracy, and example models include Faster R-CNN, Mask R-CNN and Cascade R-CNN.

The most popular benchmark is the MSCOCO dataset. Models are typically evaluated according to a Mean Average Precision metric.

( Image credit: Detectron )

Libraries

Use these libraries to find Object Detection models and implementations
PaddlePaddle/PaddleDetection
71 papers
12,094
open-mmlab/mmdetection
64 papers
27,866
rwightman/pytorch-image-models
39 papers
29,863
osmr/imgclsmob
20 papers
2,919
See all 41 libraries.

Datasets

Subtasks

Latest papers with no code

Most implemented Social Latest No code

AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models

no code yet • 24 Apr 2024

AutoGluon-Multimodal (AutoMM) is introduced as an open-source AutoML library designed specifically for multimodal learning.

 
Paper
Add Code

Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks

no code yet • 24 Apr 2024

Latency attacks against object detection represent a variant of adversarial attacks that aim to inflate the inference time by generating additional ghost objects in a target image.

 
Paper
Add Code

Efficient Transformer Encoders for Mask2Former-style models

no code yet • 23 Apr 2024

The third step is to use the aforementioned derived dataset to train a gating network that predicts the number of encoder layers to be used, conditioned on the input image.

 
Paper
Add Code

Source-free Domain Adaptation for Video Object Detection Under Adverse Image Conditions

no code yet • 23 Apr 2024

When deploying pre-trained video object detectors in real-world scenarios, the domain gap between training and testing data caused by adverse image conditions often leads to performance degradation.

 
Paper
Add Code

Gallbladder Cancer Detection in Ultrasound Images based on YOLO and Faster R-CNN

no code yet • 23 Apr 2024

A fusion method that leverages the benefits of both techniques is presented in this study.

 
Paper
Add Code

External Prompt Features Enhanced Parameter-efficient Fine-tuning for Salient Object Detection

no code yet • 23 Apr 2024

To better harness the potential of transformers for SOD, we propose a novel parameter-efficient fine-tuning method aimed at reducing the number of training parameters while enhancing the salient object detection capability.

 
Paper
Add Code

ContextualFusion: Context-Based Multi-Sensor Fusion for 3D Object Detection in Adverse Operating Conditions

no code yet • 23 Apr 2024

The fusion of multimodal sensor data streams such as camera images and lidar point clouds plays an important role in the operation of autonomous vehicles (AVs).

 
Paper
Add Code

CFPFormer: Feature-pyramid like Transformer Decoder for Segmentation and Detection

no code yet • 23 Apr 2024

Feature pyramids have been widely adopted in convolutional neural networks (CNNs) and transformers for tasks like medical image segmentation and object detection.

 
Paper
Add Code

CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective

no code yet • 22 Apr 2024

Note that constraints on intra-sample similarities and inter-sample dissimilarities can be efficiently and effectively reformulated into a contrastive learning framework with newly designed positive and negative pairs.

 
Paper
Add Code

NeRF-DetS: Enhancing Multi-View 3D Object Detection with Sampling-adaptive Network of Continuous NeRF-based Representation

no code yet • 22 Apr 2024

As a preliminary work, NeRF-Det unifies the tasks of novel view synthesis and 3D perception, demonstrating that perceptual tasks can benefit from novel view synthesis methods like NeRF, significantly improving the performance of indoor multi-view 3D object detection.

 
Paper
Add Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy