DeepAI AI Chat
Log In Sign Up

Generalized Few-Shot Object Detection without Forgetting

by   Zhibo Fan, et al.

Recently few-shot object detection is widely adopted to deal with data-limited situations. While most previous works merely focus on the performance on few-shot categories, we claim that detecting all classes is crucial as test samples may contain any instances in realistic applications, which requires the few-shot detector to learn new concepts without forgetting. Through analysis on transfer learning based methods, some neglected but beneficial properties are utilized to design a simple yet effective few-shot detector, Retentive R-CNN. It consists of Bias-Balanced RPN to debias the pretrained RPN and Re-detector to find few-shot class objects without forgetting previous knowledge. Extensive experiments on few-shot detection benchmarks show that Retentive R-CNN significantly outperforms state-of-the-art methods on overall performance among all settings as it can achieve competitive results on few-shot classes and does not degrade the base class performance at all. Our approach has demonstrated that the long desired never-forgetting learner is available in object detection.


page 3

page 8

page 11

page 12

page 13


Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning

Incremental few-shot object detection aims at detecting novel classes wi...

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

Few-shot object detection is an imperative and long-lasting problem due ...

Fast Hierarchical Learning for Few-Shot Object Detection

Transfer learning based approaches have recently achieved promising resu...

Few-Shot Learning for Video Object Detection in a Transfer-Learning Scheme

Different from static images, videos contain additional temporal and spa...

Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection

We study the challenging incremental few-shot object detection (iFSD) se...

CFA: Constraint-based Finetuning Approach for Generalized Few-Shot Object Detection

Few-shot object detection (FSOD) seeks to detect novel categories with l...

DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection

Few-shot object detection, which aims at detecting novel objects rapidly...

Code Repositories


This project provides an implementation for "Generalized Few-Shot Object Detection without Forgetting" (CVPR2021) on PyTorch.

view repo