Log In Sign Up

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

by   Bohao Li, et al.

Few-shot object detection has made substantial progressby representing novel class objects using the feature representation learned upon a set of base class objects. However,an implicit contradiction between novel class classification and representation is unfortunately ignored. On the one hand, to achieve accurate novel class classification, the distributions of either two base classes must be far away fromeach other (max-margin). On the other hand, to precisely represent novel classes, the distributions of base classes should be close to each other to reduce the intra-class distance of novel classes (min-margin). In this paper, we propose a class margin equilibrium (CME) approach, with the aim to optimize both feature space partition and novel class reconstruction in a systematic way. CME first converts the few-shot detection problem to the few-shot classification problem by using a fully connected layer to decouple localization features. CME then reserves adequate margin space for novel classes by introducing simple-yet-effective class margin loss during feature learning. Finally, CME pursues margin equilibrium by disturbing the features of novel class instances in an adversarial min-max fashion. Experiments on Pascal VOC and MS-COCO datasets show that CME significantly improves upon two baseline detectors (up to 3 ∼ 5 state-of-the-art performance. Code is available at .


page 3

page 4

page 6

page 8


Few-Shot Object Detection via Association and DIscrimination

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

Negative Margin Matters: Understanding Margin in Few-shot Classification

This paper introduces a negative margin loss to metric learning based fe...

Constrained Few-shot Class-incremental Learning

Continually learning new classes from fresh data without forgetting prev...

Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detection

Few-shot object detection (FSOD) localizes and classifies objects in an ...

Class Equilibrium using Coulomb's Law

Projection algorithms learn a transformation function to project the dat...

Morphable Detector for Object Detection on Demand

Many emerging applications of intelligent robots need to explore and und...

OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features

In this paper, we consider the task of one-shot object detection, which ...