High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and its Applications to High-Level Vision

TL;DR

This paper introduces a boundary detection method that leverages high-level object features from pretrained networks, achieving state-of-the-art accuracy and enhancing high-level vision tasks like segmentation and object proposal generation.

Contribution

The work presents a novel high-for-low boundary detection approach using object-level features, and demonstrates its effectiveness in improving multiple high-level vision tasks.

Findings

Achieves state-of-the-art boundary detection performance

Improves semantic boundary labeling, segmentation, and object proposals

Provides an efficient and generalizable boundary detection system

Abstract

Most of the current boundary detection systems rely exclusively on low-level features, such as color and texture. However, perception studies suggest that humans employ object-level reasoning when judging if a particular pixel is a boundary. Inspired by this observation, in this work we show how to predict boundaries by exploiting object-level features from a pretrained object-classification network. Our method can be viewed as a "High-for-Low" approach where high-level object features inform the low-level boundary detection process. Our model achieves state-of-the-art performance on an established boundary detection benchmark and it is efficient to run. Additionally, we show that due to the semantic nature of our boundaries we can use them to aid a number of high-level vision tasks. We demonstrate that using our boundaries we improve the performance of state-of-the-art methods on the problems of semantic boundary labeling, semantic segmentation and object proposal generation. We can view this process as a "Low-for-High" scheme, where low-level boundaries aid high-level vision tasks. Thus, our contributions include a boundary detection system that is accurate, efficient, generalizes well to multiple datasets, and is also shown to improve existing state-of-the-art high-level vision methods on three distinct tasks.