Learnable Tree Filter for Structure-preserving Feature Transform

09/27/2019
by   Lin Song, et al.
0

Learning discriminative global features plays a vital role in semantic segmentation. And most of the existing methods adopt stacks of local convolutions or non-local blocks to capture long-range context. However, due to the absence of spatial structure preservation, these operators ignore the object details when enlarging receptive fields. In this paper, we propose the learnable tree filter to form a generic tree filtering module that leverages the structural property of minimal spanning tree to model long-range dependencies while preserving the details. Furthermore, we propose a highly efficient linear-time algorithm to reduce resource consumption. Thus, the designed modules can be plugged into existing deep neural networks conveniently. To this end, tree filtering modules are embedded to formulate a unified framework for semantic segmentation. We conduct extensive ablation studies to elaborate on the effectiveness and efficiency of the proposed method. Specifically, it attains better performance with much less overhead compared with the classic PSP block and Non-local operation under the same backbone. Our approach is proved to achieve consistent improvements on several benchmarks without bells-and-whistles. Code and models are available at https://github.com/StevenGrove/TreeFilter-Torch.

READ FULL TEXT

page 6

page 7

research
12/07/2020

Rethinking Learnable Tree Filter for Generic Feature Transform

The Learnable Tree Filter presents a remarkable approach to model struct...
research
08/21/2019

Asymmetric Non-local Neural Networks for Semantic Segmentation

The non-local module works as a particularly useful technique for semant...
research
07/28/2021

Global Aggregation then Local Distribution for Scene Parsing

Modelling long-range contextual relationships is critical for pixel-wise...
research
12/17/2020

Semi-Global Shape-aware Network

Non-local operations are usually used to capture long-range dependencies...
research
12/24/2020

Global Context Networks

The Non-Local Network (NLNet) presents a pioneering approach for capturi...
research
04/25/2019

GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond

The Non-Local Network (NLNet) presents a pioneering approach for capturi...
research
08/05/2021

Unifying Nonlocal Blocks for Neural Networks

The nonlocal-based blocks are designed for capturing long-range spatial-...

Please sign up or login with your details

Forgot password? Click here to reset