Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Xianyu, Jiang, Ming, Zhao, Qi
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913566370562048
author Chen, Xianyu
Jiang, Ming
Zhao, Qi
author_facet Chen, Xianyu
Jiang, Ming
Zhao, Qi
contents Few-shot object detection aims at detecting objects with few annotated examples, which remains a challenging research problem yet to be explored. Recent studies have shown the effectiveness of self-learned top-down attention mechanisms in object detection and other vision tasks. The top-down attention, however, is less effective at improving the performance of few-shot detectors. Due to the insufficient training data, object detectors cannot effectively generate attention maps for few-shot examples. To improve the performance and interpretability of few-shot object detectors, we propose an attentive few-shot object detection network (AttFDNet) that takes the advantages of both top-down and bottom-up attention. Being task-agnostic, the bottom-up attention serves as a prior that helps detect and localize naturally salient objects. We further address specific challenges in few-shot object detection by introducing two novel loss terms and a hybrid few-shot learning strategy. Experimental results and visualization demonstrate the complementary nature of the two types of attention and their roles in few-shot object detection. Codes are available at https://github.com/chenxy99/AttFDNet.
format Preprint
id arxiv_https___arxiv_org_abs_2007_12104
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection
Chen, Xianyu
Jiang, Ming
Zhao, Qi
Computer Vision and Pattern Recognition
Few-shot object detection aims at detecting objects with few annotated examples, which remains a challenging research problem yet to be explored. Recent studies have shown the effectiveness of self-learned top-down attention mechanisms in object detection and other vision tasks. The top-down attention, however, is less effective at improving the performance of few-shot detectors. Due to the insufficient training data, object detectors cannot effectively generate attention maps for few-shot examples. To improve the performance and interpretability of few-shot object detectors, we propose an attentive few-shot object detection network (AttFDNet) that takes the advantages of both top-down and bottom-up attention. Being task-agnostic, the bottom-up attention serves as a prior that helps detect and localize naturally salient objects. We further address specific challenges in few-shot object detection by introducing two novel loss terms and a hybrid few-shot learning strategy. Experimental results and visualization demonstrate the complementary nature of the two types of attention and their roles in few-shot object detection. Codes are available at https://github.com/chenxy99/AttFDNet.
title Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2007.12104