Proposal Distribution Calibration for Few-Shot Object Detection

by   Bohao Li, et al.

Adapting object detectors learned with sufficient supervision to novel classes under low data regimes is charming yet challenging. In few-shot object detection (FSOD), the two-step training paradigm is widely adopted to mitigate the severe sample imbalance, i.e., holistic pre-training on base classes, then partial fine-tuning in a balanced setting with all classes. Since unlabeled instances are suppressed as backgrounds in the base training phase, the learned RPN is prone to produce biased proposals for novel instances, resulting in dramatic performance degradation. Unfortunately, the extreme data scarcity aggravates the proposal distribution bias, hindering the RoI head from evolving toward novel classes. In this paper, we introduce a simple yet effective proposal distribution calibration (PDC) approach to neatly enhance the localization and classification abilities of the RoI head by recycling its localization ability endowed in base training and enriching high-quality positive samples for semantic fine-tuning. Specifically, we sample proposals based on the base proposal statistics to calibrate the distribution bias and impose additional localization and classification losses upon the sampled proposals for fast expanding the base detector to novel classes. Experiments on the commonly used Pascal VOC and MS COCO datasets with explicit state-of-the-art performances justify the efficacy of our PDC for FSOD. Code is available at


page 1

page 3

page 7


Few-Shot Object Detection with Proposal Balance Refinement

Few-shot object detection has gained significant attention in recent yea...

Few-Shot Object Detection via Association and DIscrimination

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

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

Most of existing methods for few-shot object detection follow the fine-t...

Low-shot Object Detection via Classification Refinement

This work aims to address the problem of low-shot object detection, wher...

Exploring Effective Knowledge Transfer for Few-shot Object Detection

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

Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection

Two-stage object detectors generate object proposals and classify them t...

Sequential Optimization for Efficient High-Quality Object Proposal Generation

We are motivated by the need for a generic object proposal generation al...

Please sign up or login with your details

Forgot password? Click here to reset