One-Shot Object Detection with Co-Attention and Co-Excitation (2019-11-28T00:00:00.000000Z)

TL;DR

A novel CoAE framework that develops a squeeze-and-co-excitation scheme that can adaptively emphasize correlated feature channels to help uncover relevant proposals and eventually the target objects, and designs a margin-based ranking loss for implicitly learning a metric to predict the similarity of a region proposal to the underlying query.

Abstract

This paper aims to tackle the challenging problem of one-shot object detection. Given a query image patch whose class label is not included in the training data, the goal of the task is to detect all instances of the same class in a target image. To this end, we develop a novel {\em co-attention and co-excitation} (CoAE) framework that makes contributions in three key technical aspects. First, we propose to use the non-local operation to explore the co-attention embodied in each query-target pair and yield region proposals accounting for the one-shot situation. Second, we formulate a squeeze-and-co-excitation scheme that can adaptively emphasize correlated feature channels to help uncover relevant proposals and eventually the target objects. Third, we design a margin-based ranking loss for implicitly learning a metric to predict the similarity of a region proposal to the underlying query, no matter its class label is seen or unseen in training. The resulting model is therefore a two-stage detector that yields a strong baseline on both VOC and MS-COCO under one-shot setting of detecting objects from both seen and never-seen classes.

Authors

Hwann-Tzong Chen

5 papers

Ting-I Hsieh

1 papers

Yi-Chen Lo

1 papers

One-Shot Object Detection with Co-Attention and Co-Excitation

TL;DR

Abstract

Authors

References29 items

FoveaBox: Beyond Anchor-based Object Detector

Comparison Network for One-Shot Conditional Object Detection

Few-Shot Object Detection via Feature Reweighting

One-Shot Instance Segmentation

Fully Convolutional Siamese Fusion Networks for Object Tracking

CornerNet: Detecting Objects as Paired Keypoints

RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection

High Performance Visual Tracking with Siamese Region Proposal Network

LSTD: A Low-Shot Transfer Detector for Object Detection

Cascade R-CNN: Delving Into High Quality Object Detection

Non-local Neural Networks

Learning to Compare: Relation Network for Few-Shot Learning

Squeeze-and-Excitation Networks

Focal Loss for Dense Object Detection

Mask R-CNN

Prototypical Networks for Few-shot Learning

Feature Pyramid Networks for Object Detection

Matching Networks for One Shot Learning

SSD: Single Shot MultiBox Detector

Pointer Networks

You Only Look Once: Unified, Real-Time Object Detection

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Fast R-CNN

Neural Machine Translation by Jointly Learning to Align and Translate

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Vision Science Photons To Phenomenology

Siamese Neural Networks for One-Shot Image Recognition

Field of Study

Venue Information

Name

Type

URL

Alternate Names