DeepAI AI Chat
Log In Sign Up

Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection

by   Shuang Wu, et al.
Harbin Institute of Technology

Most of existing methods for few-shot object detection follow the fine-tuning paradigm, which potentially assumes that the class-agnostic generalizable knowledge can be learned and transferred implicitly from base classes with abundant samples to novel classes with limited samples via such a two-stage training strategy. However, it is not necessarily true since the object detector can hardly distinguish between class-agnostic knowledge and class-specific knowledge automatically without explicit modeling. In this work we propose to learn three types of class-agnostic commonalities between base and novel classes explicitly: recognition-related semantic commonalities, localization-related semantic commonalities and distribution commonalities. We design a unified distillation framework based on a memory bank, which is able to perform distillation of all three types of commonalities jointly and efficiently. Extensive experiments demonstrate that our method can be readily integrated into most of existing fine-tuning based methods and consistently improve the performance by a large margin.


page 14

page 22


Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations

While fine-tuning based methods for few-shot object detection have achie...

Few-Shot Object Detection via Association and DIscrimination

Object detection has achieved substantial progress in the last decade. H...

Incremental Few-Shot Object Detection via Simple Fine-Tuning Approach

In this paper, we explore incremental few-shot object detection (iFSD), ...

Proposal Distribution Calibration for Few-Shot Object Detection

Adapting object detectors learned with sufficient supervision to novel c...

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

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

Exploring Effective Knowledge Transfer for Few-shot Object Detection

Recently, few-shot object detection (FSOD) has received much attention f...

In defense of OSVOS

As a milestone for video object segmentation, one-shot video object segm...