1727 papers with code • 54 benchmarks • 165 datasets
Object detection is the task of detecting instances of objects of a certain class within an image. 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 )
- 3D Object Detection
- RGB Salient Object Detection
- Real-Time Object Detection
- 2D Object Detection
- 2D Object Detection
- Video Object Detection
- RGB-D Salient Object Detection
- Few-Shot Object Detection
- Weakly Supervised Object Detection
- Small Object Detection
- Object Detection In Aerial Images
- Object Proposal Generation
- Robust Object Detection
- Video Salient Object Detection
- Dense Object Detection
- Head Detection
- Camouflaged Object Segmentation
- Co-Salient Object Detection
- Zero-Shot Object Detection
- Medical Object Detection
- One-Shot Object Detection
- Moving Object Detection
- Surgical tool detection
- Multiview Detection
- Semantic Part Detection
- Object Skeleton Detection
- Open World Object Detection
- Multiple Affordance Detection
- 3D Object Detection From Monocular Images
- Fish Detection
- Class-agnostic Object Detection
- Object Detection In Indoor Scenes
Adder neural networks (AdderNets) have shown impressive performance on image classification with only addition operations, which are more energy efficient than traditional convolutional neural networks built with multiplications.
In this paper, we take a step further by proposing a novel generative vision transformer with latent variables following an informative energy-based prior for salient object detection.
In this work we propose Recurrent Bayesian Classifier Chains (RBCCs), which learn a Bayesian network of class dependencies and leverage this network in order to condition the prediction of child nodes only on their parents.
In this paper, we propose Parameterized AP Loss, where parameterized functions are introduced to substitute the non-differentiable components in the AP calculation.
SSAL: Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
In this paper, we propose to leverage model’s predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment.