Semantic Part Detection via Matching: Learning to Generalize to Novel Viewpoints From Limited Training Data (2018-11-28T00:00:00.000000Z)

TL;DR

This paper presents an approach which can learn from a small annotated dataset containing a limited range of viewpoints and generalize to detect semantic parts for a much largerrange of viewpoints.

Abstract

Detecting semantic parts of an object is a challenging task, particularly because it is hard to annotate semantic parts and construct large datasets. In this paper, we present an approach which can learn from a small annotated dataset containing a limited range of viewpoints and generalize to detect semantic parts for a much larger range of viewpoints. The approach is based on our matching algorithm, which is used for finding accurate spatial correspondence between two images and transplanting semantic parts annotated on one image to the other. Images in the training set are matched to synthetic images rendered from a 3D CAD model, following which a clustering algorithm is used to automatically annotate semantic parts of the CAD model. During the testing period, this CAD model can synthesize annotated images under every viewpoint. These synthesized images are matched to images in the testing set to detect semantic parts in novel viewpoints. Our algorithm is simple, intuitive, and contains very few parameters. Experiments show our method outperforms standard deep learning approaches and, in particular, performs much better on novel viewpoints. For facilitating the future research, code is available: https://github.com/ytongbai/SemanticPartDetection

Authors

A. Yuille

29 papers

Weichao Qiu

4 papers

Lingxi Xie

6 papers

TL;DR

Abstract

Authors

References64 items

FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence

Acquisition of Localization Confidence for Accurate Object Detection

DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection Under Partial Occlusion

DeepVoting: An Explainable Framework for Semantic Part Detection under Partial Occlusion

Squeeze-and-Excitation Networks

Detecting Semantic Parts on Partially Occluded Objects

Deep Semantic Feature Matching

SCNet: Learning Semantic Correspondence

Learning Non-maximum Suppression

Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings

AnchorNet: A Weakly Supervised Network to Learn Geometry-Sensitive Features for Semantic Matching

Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks

Click Here: Human-Localized Keypoints as Guidance for Viewpoint Estimation

Adversarial Examples for Semantic Segmentation and Object Detection

Proposal Flow: Semantic Correspondences from Object Proposals

Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Unsupervised Monocular Depth Estimation with Left-Right Consistency

UnrealCV: Connecting Computer Vision to Unreal Engine

Densely Connected Convolutional Networks

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Learning Dense Correspondence via 3D-Guided Cycle Consistency

LIFT: Learned Invariant Feature Transform

Stacked Hourglass Networks for Human Pose Estimation

Deep Residual Learning for Image Recognition

SSD: Single Shot MultiBox Detector

Unsupervised learning of object semantic parts from internal states of CNNs by population encoding

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

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

Fast R-CNN

FlowNet: Learning Optical Flow with Convolutional Networks

Holistically-Nested Edge Detection

Robust $L_{2}E$ Estimation of Transformation for Non-Rigid Registration

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Object Detectors Emerge in Deep Scene CNNs

Fully convolutional networks for semantic segmentation

Going deeper with convolutions

Very Deep Convolutional Networks for Large-Scale Image Recognition

DAISY Filter Flow: A Generalized Discrete Approach to Dense Correspondences

Microsoft COCO: Common Objects in Context

Beyond PASCAL: A benchmark for 3D object detection in the wild

CNN Features Off-the-Shelf: An Astounding Baseline for Recognition

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

Selective Search for Object Recognition

ImageNet classification with deep convolutional neural networks

Viewpoint-aware object detection and continuous pose estimation

Nonparametric Scene Parsing via Label Transfer

Measuring the Objectness of Image Windows

Fast cost-volume filtering for visual correspondence and beyond

SIFT Flow: Dense Correspondence across Scenes and Its Applications

Object Detection with Discriminatively Trained Part Based Models

Rectified Linear Units Improve Restricted Boltzmann Machines

Pose estimation for category specific multiview object localization

ImageNet: A large-scale hierarchical image database

Et al

Histograms of oriented gradients for human detection

Robust wide-baseline stereo from maximally stable extremal regions

A multiple-baseline stereo

Deep Learning

Dropout: a simple way to prevent neural networks from overfitting

International Journal of Computer Vision manuscript No. (will be inserted by the editor) The PASCAL Visual Object Classes (VOC) Challenge

AND T

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names