Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation

Abstract

This paper proposes a novel heterogeneous grid convolution that builds a graph-based image representation by exploiting heterogeneity in the image content, enabling adaptive, efficient, and controllable computations in a convolutional architecture. More concretely, the approach builds a data-adaptive graph structure from a convolutional layer by a differentiable clustering method, pools features to the graph, performs a novel direction-aware graph convolution, and unpool features back to the convolutional layer. By using the developed module, the paper proposes heterogeneous grid convolutional networks, highly efficient yet strong extension of existing architectures. We have evaluated the proposed approach on four image understanding tasks, semantic segmentation, object localization, road extraction, and salient object detection. The proposed method is effective on three of the four tasks. Especially, the method outperforms a strong baseline with more than 90% reduction in floating-point operations for semantic segmentation, and achieves the state-of-the-art result for road extraction. We will share our code, model, and data.

Accepted to CVPR 2021

References in corpus (6)

• Learning Deconvolution Network for Semantic Segmentation
• Visual Saliency Based on Multiscale Deep Features
• Position-aware Graph Neural Networks
• ACFNet: Attentional Class Feature Network for Semantic Segmentation
• Suppress and Balance: A Simple Gated Network for Salient Object Detection
• Efficient Segmentation: Learning Downsampling Near Semantic Boundaries