DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection

03/16/2023
by   Jiawei Ma, et al.
0

Generalized few-shot object detection aims to achieve precise detection on both base classes with abundant annotations and novel classes with limited training data. Existing approaches enhance few-shot generalization with the sacrifice of base-class performance, or maintain high precision in base-class detection with limited improvement in novel-class adaptation. In this paper, we point out the reason is insufficient Discriminative feature learning for all of the classes. As such, we propose a new training framework, DiGeo, to learn Geometry-aware features of inter-class separation and intra-class compactness. To guide the separation of feature clusters, we derive an offline simplex equiangular tight frame (ETF) classifier whose weights serve as class centers and are maximally and equally separated. To tighten the cluster for each class, we include adaptive class-specific margins into the classification loss and encourage the features close to the class centers. Experimental studies on two few-shot benchmark datasets (VOC, COCO) and one long-tail dataset (LVIS) demonstrate that, with a single model, our method can effectively improve generalization on novel classes without hurting the detection of base classes.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/23/2021

Towards Generalized and Incremental Few-Shot Object Detection

Real-world object detection is highly desired to be equipped with the le...
research
01/20/2016

Factors in Finetuning Deep Model for object detection

Finetuning from a pretrained deep model is found to yield state-of-the-a...
research
03/08/2021

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

Few-shot object detection has made substantial progressby representing n...
research
03/24/2023

Adaptive Base-class Suppression and Prior Guidance Network for One-Shot Object Detection

One-shot object detection (OSOD) aims to detect all object instances tow...
research
12/23/2021

Dual Path Structural Contrastive Embeddings for Learning Novel Objects

Learning novel classes from a very few labeled samples has attracted inc...
research
10/10/2022

Fast Hierarchical Learning for Few-Shot Object Detection

Transfer learning based approaches have recently achieved promising resu...
research
03/09/2023

NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging

Privacy and memory are two recurring themes in a broad conversation abou...

Please sign up or login with your details

Forgot password? Click here to reset