TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Computer Vision/Few-Shot Object Detection

Few-Shot Object Detection

26 benchmarks179 papers

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

Few-Shot Object Detection on MS-COCO (10-shot)

AP

Few-Shot Object Detection on CAMO-FS

box AP

Few-Shot Object Detection on MS-COCO (30-shot)

AP

Few-Shot Object Detection on Artaxor

mAP

Few-Shot Object Detection on UODD

mAP

Few-Shot Object Detection on DIOR

mAP

Few-Shot Object Detection on Clipark1k

mAP

Few-Shot Object Detection on DeepFish

mAP

Few-Shot Object Detection on NEU-DET

mAP

Few-Shot Object Detection on LVIS v1.0 val

APAPrAPcAPfAP50AP75

Few-Shot Object Detection on MS-COCO (1-shot)

AP

Few-Shot Object Detection on LVIS v1.0 test-dev

APAP50AP75APrAPcAPf

Few-Shot Object Detection on ODinW-13

Average Score

Few-Shot Object Detection on ODinW-35

Average Score

Few-Shot Object Detection on COCO 2017

AP

Few-Shot Object Detection on MS-COCO (5-shot)

AP