Methods > Computer Vision > Object Detection Models

FoveaBox

Introduced by Kong et al. in FoveaBox: Beyond Anchor-based Object Detector

FoveaBox is anchor-free framework for object detection. Instead of using predefined anchors to enumerate possible locations, scales and aspect ratios for the search of the objects, FoveaBox directly learns the object existing possibility and the bounding box coordinates without anchor reference. This is achieved by: (a) predicting category-sensitive semantic maps for the object existing possibility, and (b) producing category-agnostic bounding box for each position that potentially contains an object. The scales of target boxes are naturally associated with feature pyramid representations for each input image

It is a single, unified network composed of a backbone network and two task-specific subnetworks. The backbone is responsible for computing a convolutional feature map over an entire input image and is an off-the-shelf convolutional network. The first subnet performs per pixel classification on the backbone’s output; the second subnet performs bounding box prediction for the corresponding position.

Source: FoveaBox: Beyond Anchor-based Object Detector

Latest Papers

PAPER DATE
FoveaBox: Beyound Anchor-based Object Detection
Tao KongFuchun SunHuaping LiuYuning JiangLei LiJianbo Shi
2020-01-01
FoveaBox: Beyond Anchor-based Object Detector
| Tao KongFuchun SunHuaping LiuYuning JiangLei LiJianbo Shi
2019-04-08

Tasks

TASK PAPERS SHARE
Object Detection 2 100.00%

Components

COMPONENT TYPE
FPN
Feature Extractors

Categories