Deformable Part-based Fully Convolutional Network for Object Detection

TL;DR

This paper introduces DP-FCN, a deformable part-based fully convolutional network that adapts to object shapes for improved detection accuracy, achieving state-of-the-art results on PASCAL VOC datasets.

Contribution

The paper presents a novel deformable part-based FCN architecture that learns to adapt to object shapes without extra annotations, enhancing detection and localization.

Findings

Achieves 83.1% mAP on PASCAL VOC 2007

Achieves 80.9% mAP on PASCAL VOC 2012

Significant performance improvements over previous methods

Abstract

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 discriminative elements and to align them, and simultaneously brings more invariance for classification 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 invariance, 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.