Few-Shot Object Detection via Variational Feature Aggregation

by   Jiaming Han, et al.
Wuhan University

As few-shot object detectors are often trained with abundant base samples and fine-tuned on few-shot novel examples,the learned models are usually biased to base classes and sensitive to the variance of novel examples. To address this issue, we propose a meta-learning framework with two novel feature aggregation schemes. More precisely, we first present a Class-Agnostic Aggregation (CAA) method, where the query and support features can be aggregated regardless of their categories. The interactions between different classes encourage class-agnostic representations and reduce confusion between base and novel classes. Based on the CAA, we then propose a Variational Feature Aggregation (VFA) method, which encodes support examples into class-level support features for robust feature aggregation. We use a variational autoencoder to estimate class distributions and sample variational features from distributions that are more robust to the variance of support examples. Besides, we decouple classification and regression tasks so that VFA is performed on the classification branch without affecting object localization. Extensive experiments on PASCAL VOC and COCO demonstrate that our method significantly outperforms a strong baseline (up to 16%) and previous state-of-the-art methods (4% in average). Code will be available at: <https://github.com/csuhan/VFA>


page 4

page 7

page 11


Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection

Few-shot object detection has made substantial progressby representing n...

Generating Representative Samples for Few-Shot Classification

Few-shot learning (FSL) aims to learn new categories with a few visual s...

Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection

Conventional deep learning based methods for object detection require a ...

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

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

Learning What Not to Segment: A New Perspective on Few-Shot Segmentation

Recently few-shot segmentation (FSS) has been extensively developed. Mos...

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

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

Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation

Few-shot segmentation (FSS) aims to segment unseen classes given only a ...

Please sign up or login with your details

Forgot password? Click here to reset