Towards Efficient Scene Understanding via Squeeze Reasoning

by   Xiangtai Li, et al.

Graph-based convolutional model such as non-local block has shown to be effective for strengthening the context modeling ability in convolutional neural networks (CNNs). However, its pixel-wise computational overhead is prohibitive which renders it unsuitable for high resolution imagery. In this paper, we explore the efficiency of context graph reasoning and propose a novel framework called Squeeze Reasoning. Instead of propagating information on the spatial map, we first learn to squeeze the input feature into a channel-wise global vector and perform reasoning within the single vector where the computation cost can be significantly reduced. Specifically, we build the node graph in the vector where each node represents an abstract semantic concept. The refined feature within the same semantic category results to be consistent, which is thus beneficial for downstream tasks. We show that our approach can be modularized as an end-to-end trained block and can be easily plugged into existing networks. Despite its simplicity and being lightweight, our strategy allows us to establish a new state-of-the-art on semantic segmentation and show significant improvements with respect to strong, state-of-the-art baselines on various other scene understanding tasks including object detection, instance segmentation and panoptic segmentation. Code will be made available to foster any further research


page 1

page 7

page 8

page 9

page 10


Global Aggregation then Local Distribution for Scene Parsing

Modelling long-range contextual relationships is critical for pixel-wise...

Efficient Hybrid Transformer: Learning Global-local Context for Urban Sence Segmentation

Semantic segmentation of fine-resolution urban scene images plays a vita...

CABiNet: Efficient Context Aggregation Network for Low-Latency Semantic Segmentation

With the increasing demand of autonomous machines, pixel-wise semantic s...

Bidirectional Graph Reasoning Network for Panoptic Segmentation

Recent researches on panoptic segmentation resort to a single end-to-end...

Graph-Based Global Reasoning Networks

Globally modeling and reasoning over relations between regions can be be...

Towards holistic scene understanding: Semantic segmentation and beyond

This dissertation addresses visual scene understanding and enhances segm...

Spectral Analysis for Semantic Segmentation with Applications on Feature Truncation and Weak Annotation

The current neural networks for semantic segmentation usually predict th...

Please sign up or login with your details

Forgot password? Click here to reset