One-Shot Object Detection
10 papers with code • 2 benchmarks • 2 datasets
( Image credit: Siamese Mask R-CNN )
Benchmarks
These leaderboards are used to track progress in One-Shot Object Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
MS COCO
SKU110K
Latest papers
Detect Everything with Few Examples
mlzxy/devit
•
•
DE-ViT establishes new state-of-the-art results on all benchmarks.
Simple Open-Vocabulary Object Detection with Vision Transformers
Combining simple architectures with large-scale pre-training has led to massive improvements in image classification.
Balanced and Hierarchical Relation Learning for One-Shot Object Detection
hero-y/bhrl
•
•
CVPR 2022
In this paper, we introduce the balanced and hierarchical learning for our detector.
Quasi-Dense Similarity Learning for Multiple Object Tracking
Compared to methods with similar detectors, it boosts almost 10 points of MOTA and significantly decreases the number of ID switches on BDD100K and Waymo datasets.
One-Shot Object Detection without Fine-Tuning
Deep learning has revolutionized object detection thanks to large-scale datasets, but their object categories are still arguably very limited.
OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features
In this paper, we consider the task of one-shot object detection, which consists in detecting objects defined by a single demonstration.
One-Shot Object Detection with Co-Attention and Co-Excitation
timy90022/One-Shot-Object-Detection
•
•
NeurIPS 2019
This paper aims to tackle the challenging problem of one-shot object detection.
One-Shot Instance Segmentation
bethgelab/siamese-mask-rcnn
•
•
We demonstrate empirical results on MS Coco highlighting challenges of the one-shot setting: while transferring knowledge about instance segmentation to novel object categories works very well, targeting the detection network towards the reference category appears to be more difficult.
DroNet: Efficient convolutional neural network detector for real-time UAV applications
Through the analysis we propose a CNN architecture that is capable of detecting vehicles from aerial UAV images and can operate between 5-18 frames-per-second for a variety of platforms with an overall accuracy of ~95%.
RepMet: Representative-based metric learning for classification and one-shot object detection
jshtok/RepMet
•
•
Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples.
