Modern object detectors rely heavily on rectangular bounding boxes, such as
anchors, proposals and the final predictions, to represent objects at various
recognition stages. The bounding box is convenient to use but provides only a
coarse localization of objects and leads to a correspondingly coarse extraction
of object features. In this paper, we present RepPoints
(representative points), a new finer representation of objects as a set of
sample points useful for both localization and recognition. Given ground truth
localization and recognition targets for training, RepPoints learn to
automatically arrange themselves in a manner that bounds the spatial extent of
an object and indicates semantically significant local areas. They furthermore
do not require the use of anchors to sample a space of bounding boxes. We show
that an anchor-free object detector based on RepPoints, implemented without
multi-scale training and testing, can be as effective as state-of-the-art
anchor-based detection methods, with 42.8 AP and 65.0 $AP_50$ on the COCO
test-dev detection benchmark.
Description
RepPoints: Point Set Representation for Object Detection
%0 Generic
%1 yang2019reppoints
%A Yang, Ze
%A Liu, Shaohui
%A Hu, Han
%A Wang, Liwei
%A Lin, Stephen
%D 2019
%K arch cornernet detection head loss
%T RepPoints: Point Set Representation for Object Detection
%U http://arxiv.org/abs/1904.11490
%X Modern object detectors rely heavily on rectangular bounding boxes, such as
anchors, proposals and the final predictions, to represent objects at various
recognition stages. The bounding box is convenient to use but provides only a
coarse localization of objects and leads to a correspondingly coarse extraction
of object features. In this paper, we present RepPoints
(representative points), a new finer representation of objects as a set of
sample points useful for both localization and recognition. Given ground truth
localization and recognition targets for training, RepPoints learn to
automatically arrange themselves in a manner that bounds the spatial extent of
an object and indicates semantically significant local areas. They furthermore
do not require the use of anchors to sample a space of bounding boxes. We show
that an anchor-free object detector based on RepPoints, implemented without
multi-scale training and testing, can be as effective as state-of-the-art
anchor-based detection methods, with 42.8 AP and 65.0 $AP_50$ on the COCO
test-dev detection benchmark.
@misc{yang2019reppoints,
abstract = {Modern object detectors rely heavily on rectangular bounding boxes, such as
anchors, proposals and the final predictions, to represent objects at various
recognition stages. The bounding box is convenient to use but provides only a
coarse localization of objects and leads to a correspondingly coarse extraction
of object features. In this paper, we present \textbf{RepPoints}
(representative points), a new finer representation of objects as a set of
sample points useful for both localization and recognition. Given ground truth
localization and recognition targets for training, RepPoints learn to
automatically arrange themselves in a manner that bounds the spatial extent of
an object and indicates semantically significant local areas. They furthermore
do not require the use of anchors to sample a space of bounding boxes. We show
that an anchor-free object detector based on RepPoints, implemented without
multi-scale training and testing, can be as effective as state-of-the-art
anchor-based detection methods, with 42.8 AP and 65.0 $AP_{50}$ on the COCO
test-dev detection benchmark.},
added-at = {2019-05-22T17:55:30.000+0200},
author = {Yang, Ze and Liu, Shaohui and Hu, Han and Wang, Liwei and Lin, Stephen},
biburl = {https://www.bibsonomy.org/bibtex/2eab2d4f88cb588ef8538bb3561e9d771/nmatsuk},
description = {RepPoints: Point Set Representation for Object Detection},
interhash = {da0733ae40896b3fd40b095fc6102e72},
intrahash = {eab2d4f88cb588ef8538bb3561e9d771},
keywords = {arch cornernet detection head loss},
note = {cite arxiv:1904.11490},
timestamp = {2019-05-22T17:55:30.000+0200},
title = {RepPoints: Point Set Representation for Object Detection},
url = {http://arxiv.org/abs/1904.11490},
year = 2019
}