[MTC17] Deformable Part-based Fully Convolutional Network for Object Detection

Conférence Internationale avec comité de lecture : British Machine Vision Conference (BMVC), September 2017, UK,
Résumé: Existing region-based object detectors are limited to regions with fixed box geometry to represent objects, even if those are highly non-rectangular. In this paper we introduce DP-FCN, a deep model for object detection which explicitly adapts to shapes of objects with deformable parts. Without additional annotations, it learns to focus on discrimina- tive elements and to align them, and simultaneously brings more invariance for classifi- cation and geometric information to refine localization. DP-FCN is composed of three main modules: a Fully Convolutional Network to efficiently maintain spatial resolution, a deformable part-based RoI pooling layer to optimize positions of parts and build invari- ance, and a deformation-aware localization module explicitly exploiting displacements of parts to improve accuracy of bounding box regression. We experimentally validate our model and show significant gains. DP-FCN achieves state-of-the-art performances of 83.1% and 80.9% on PASCAL VOC 2007 and 2012 with VOC data only


@inproceedings {
title="{Deformable Part-based Fully Convolutional Network for Object Detection}",
author=" T. Mordan and N. Thome and M. Cord and G. Henaff ",
booktitle="{British Machine Vision Conference (BMVC)}",
address=" UK",