Delivering Arbitrary-Modal Semantic Segmentation

03/02/2023
by   Jiaming Zhang, et al.
0

Multimodal fusion can make semantic segmentation more robust. However, fusing an arbitrary number of modalities remains underexplored. To delve into this problem, we create the DeLiVER arbitrary-modal segmentation benchmark, covering Depth, LiDAR, multiple Views, Events, and RGB. Aside from this, we provide this dataset in four severe weather conditions as well as five sensor failure cases to exploit modal complementarity and resolve partial outages. To make this possible, we present the arbitrary cross-modal segmentation model CMNeXt. It encompasses a Self-Query Hub (SQ-Hub) designed to extract effective information from any modality for subsequent fusion with the RGB representation and adds only negligible amounts of parameters ( 0.01M) per additional modality. On top, to efficiently and flexibly harvest discriminative cues from the auxiliary modalities, we introduce the simple Parallel Pooling Mixer (PPX). With extensive experiments on a total of six benchmarks, our CMNeXt achieves state-of-the-art performance on the DeLiVER, KITTI-360, MFNet, NYU Depth V2, UrbanLF, and MCubeS datasets, allowing to scale from 1 to 81 modalities. On the freshly collected DeLiVER, the quad-modal CMNeXt reaches up to 66.30 with a +9.10 and our code are at: https://jamycheung.github.io/DELIVER.html.

READ FULL TEXT

page 5

page 8

page 14

page 15

research
03/09/2022

CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers

The performance of semantic segmentation of RGB images can be advanced b...
research
03/30/2023

Complementary Random Masking for RGB-Thermal Semantic Segmentation

RGB-thermal semantic segmentation is one potential solution to achieve r...
research
08/18/2023

Single Frame Semantic Segmentation Using Multi-Modal Spherical Images

In recent years, the research community has shown a lot of interest to p...
research
04/12/2022

Towards Reliable Image Outpainting: Learning Structure-Aware Multimodal Fusion with Depth Guidance

Image outpainting technology generates visually reasonable content regar...
research
04/06/2023

Exploiting the Complementarity of 2D and 3D Networks to Address Domain-Shift in 3D Semantic Segmentation

3D semantic segmentation is a critical task in many real-world applicati...
research
07/17/2020

Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation

Depth information has proven to be a useful cue in the semantic segmenta...
research
06/29/2019

RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation

Signals from RGB and depth data carry complementary information about th...

Please sign up or login with your details

Forgot password? Click here to reset