Universal-Prototype Augmentation for Few-Shot Object Detection

by   Aming Wu, et al.

Few-shot object detection (FSOD) aims to strengthen the performance of novel object detection with few labeled samples. To alleviate the constraint of few samples, enhancing the generalization ability of learned features for novel objects plays a key role. Thus, the feature learning process of FSOD should focus more on intrinsical object characteristics, which are invariant under different visual changes and therefore are helpful for feature generalization. Unlike previous attempts of the meta-learning paradigm, in this paper, we explore how to smooth object features with intrinsical characteristics that are universal across different object categories. We propose a new prototype, namely universal prototype, that is learned from all object categories. Besides the advantage of characterizing invariant characteristics, the universal prototypes alleviate the impact of unbalanced object categories. After augmenting object features with the universal prototypes, we impose a consistency loss to maximize the agreement between the augmented features and the original one, which is beneficial for learning invariant object characteristics. Thus, we develop a new framework of few-shot object detection with universal prototypes (FSOD^up) that owns the merit of feature generalization towards novel objects. Experimental results on PASCAL VOC and MS COCO demonstrate the effectiveness of FSOD^up. Particularly, for the 1-shot case of VOC Split2, FSOD^up outperforms the baseline by 6.8% in terms of mAP. Moreover, we further verify FSOD^up on a long-tail detection dataset, i.e., LVIS. And employing FSOD^up outperforms the state-of-the-art method.


page 6

page 8


Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild

Detecting objects and estimating their viewpoint in images are key tasks...

Few-Shot Object Detection by Attending to Per-Sample-Prototype

Few-shot object detection aims to detect instances of specific categorie...

MM-FSOD: Meta and metric integrated few-shot object detection

In the object detection task, CNN (Convolutional neural networks) models...

Meta-Cognition-Based Simple And Effective Approach To Object Detection

Recently, many researchers have attempted to improve deep learning-based...

Closing the Generalization Gap in One-Shot Object Detection

Despite substantial progress in object detection and few-shot learning, ...

Topic Adaptation and Prototype Encoding for Few-Shot Visual Storytelling

Visual Storytelling (VIST) is a task to tell a narrative story about a c...

Hierarchical Few-Shot Object Detection: Problem, Benchmark and Method

Few-shot object detection (FSOD) is to detect objects with a few example...

Please sign up or login with your details

Forgot password? Click here to reset