Adaptive Linear Span Network for Object Skeleton Detection

TL;DR

The paper introduces AdaLSN, an adaptive neural network architecture for object skeleton detection that automatically configures multi-scale features using neural architecture search, achieving higher accuracy and efficiency.

Contribution

Proposes AdaLSN, a novel NAS-driven network based on linear span theory for automatic multi-scale feature integration in skeleton detection.

Findings

Achieves higher accuracy than state-of-the-art methods.

Demonstrates versatility in edge detection and road extraction.

Offers better latency and accuracy trade-offs.

Abstract

Conventional networks for object skeleton detection are usually hand-crafted. Although effective, they require intensive priori knowledge to configure representative features for objects in different scale granularity.In this paper, we propose adaptive linear span network (AdaLSN), driven by neural architecture search (NAS), to automatically configure and integrate scale-aware features for object skeleton detection. AdaLSN is formulated with the theory of linear span, which provides one of the earliest explanations for multi-scale deep feature fusion. AdaLSN is materialized by defining a mixed unit-pyramid search space, which goes beyond many existing search spaces using unit-level or pyramid-level features.Within the mixed space, we apply genetic architecture search to jointly optimize unit-level operations and pyramid-level connections for adaptive feature space expansion. AdaLSN substantiates its versatility by achieving significantly higher accuracy and latency trade-off compared with state-of-the-arts. It also demonstrates general applicability to image-to-mask tasks such as edge detection and road extraction. Code is available at \href{https://github.com/sunsmarterjie/SDL-Skeleton}{\color{magenta}github.com/sunsmarterjie/SDL-Skeleton}.