DeepAI AI Chat
Log In Sign Up

Object Contour Detection with a Fully Convolutional Encoder-Decoder Network

by   Jimei Yang, et al.
University of Michigan
University of California, Merced

We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network. Different from previous low-level edge detection, our algorithm focuses on detecting higher-level object contours. Our network is trained end-to-end on PASCAL VOC with refined ground truth from inaccurate polygon annotations, yielding much higher precision in object contour detection than previous methods. We find that the learned model generalizes well to unseen object classes from the same super-categories on MS COCO and can match state-of-the-art edge detection on BSDS500 with fine-tuning. By combining with the multiscale combinatorial grouping algorithm, our method can generate high-quality segmented object proposals, which significantly advance the state-of-the-art on PASCAL VOC (improving average recall from 0.62 to 0.67) with a relatively small amount of candidates (∼1660 per image).


page 4

page 5

page 7


Learning to Refine Object Contours with a Top-Down Fully Convolutional Encoder-Decoder Network

We develop a novel deep contour detection algorithm with a top-down full...

Object Contour and Edge Detection with RefineContourNet

A ResNet-based multi-path refinement CNN is used for object contour dete...

Convolutional Oriented Boundaries

We present Convolutional Oriented Boundaries (COB), which produces multi...

Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network

With more and more household objects built on planned obsolescence and c...

DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection

Contour detection has been a fundamental component in many image segment...

Simultaneous Edge Alignment and Learning

Edge detection is among the most fundamental vision problems for its rol...

Learning Non-Lambertian Object Intrinsics across ShapeNet Categories

We consider the non-Lambertian object intrinsic problem of recovering di...

Code Repositories