Few-Shot Object Detection
76 papers with code • 8 benchmarks • 7 datasets
Few-Shot Object Detection is a computer vision task that involves detecting objects in images with limited training data. The goal is to train a model on a few examples of each object class and then use the model to detect objects in new images.
Benchmarks
These leaderboards are used to track progress in Few-Shot Object Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Few-Shot Object Detection models and implementations
MS COCO
LVIS
FSOD
ELEVATER
VizWiz-FewShot
Most implemented papers
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models
In general, these language-augmented visual models demonstrate strong transferability to a variety of datasets and tasks.
Few-shot Object Detection via Feature Reweighting
bingykang/Fewshot_Detection
•
•
ICCV 2019
The feature learner extracts meta features that are generalizable to detect novel object classes, using training data from base classes with sufficient samples.
Frustratingly Simple Few-Shot Object Detection
ucbdrive/few-shot-object-detection
•
•
ICML 2020
Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods.
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is limited.
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.
Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector
fanq15/FewX
•
•
CVPR 2020
To train our network, we contribute a new dataset that contains 1000 categories of various objects with high-quality annotations.
Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
Except for the backbone networks, however, other components such as the detector head and the feature pyramid network (FPN) remain trained from scratch, which hinders fully tapping the potential of representation models.
Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild
YoungXIAO13/FewShotDetection
•
•
ECCV 2020
In this paper, we tackle the problems of few-shot object detection and few-shot viewpoint estimation.
Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
Few-shot object detection has made substantial progressby representing novel class objects using the feature representation learned upon a set of base class objects.
FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
MegviiDetection/FSCE
•
•
CVPR 2021
We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected objects.
