Shypd.aiThe largest open index of AI toolsfew-shot-object-detection is an Open Source & Models tool that provides implementations of few-shot object detection benchmarks. It includes the official implementation of the ICML 2020 paper, "Frustratingly Simple Few-Shot Object Detection."
Trending
About
few-shot-object-detection (FsDet) offers official implementations of few-shot object detection benchmarks, including the ICML 2020 paper "Frustratingly Simple Few-Shot Object Detection." It introduces new benchmarks across PASCAL VOC, COCO, and LVIS datasets, with multiple groups of few-shot training examples and evaluation results for both base and novel classes. The repository provides benchmark results and pre-trained models for a two-stage fine-tuning approach (TFA), where the detector is first trained on abundant base classes and then fine-tuned on a small balanced training set. FsDet is modular, allowing for easy integration of custom datasets and models, serving as a general framework for future research in few-shot object detection.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
