ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation

RGB-D semantic segmentation has attracted increasing attention over the past few years. Existing methods mostly employ homogeneous convolution operators to consume the RGB and depth features, ignoring their intrinsic differences. In fact, the RGB values capture the photometric appearance properties in the projected image space, while the depth feature encodes both the shape of a local geometry as well as the base (whereabout) of it in a larger context. Compared with the base, the shape probably is more inherent and has a stronger connection to the semantics, and thus is more critical for segmentation accuracy. Inspired by this observation, we introduce a Shape-aware Convolutional layer (ShapeConv) for processing the depth feature, where the depth feature is firstly decomposed into a shape-component and a base-component, next two learnable weights are introduced to cooperate with them independently, and finally a convolution is applied on the re-weighted combination of these two components. ShapeConv is model-agnostic and can be easily integrated into most CNNs to replace vanilla convolutional layers for semantic segmentation. Extensive experiments on three challenging indoor RGB-D semantic segmentation benchmarks, i.e., NYU-Dv2(-13,-40), SUN RGB-D, and SID, demonstrate the effectiveness of our ShapeConv when employing it over five popular architectures. Moreover, the performance of CNNs with ShapeConv is boosted without introducing any computation and memory increase in the inference phase. The reason is that the learnt weights for balancing the importance between the shape and base components in ShapeConv become constants in the inference phase, and thus can be fused into the following convolution, resulting in a network that is identical to one with vanilla convolutional layers.

PDF Abstract ICCV 2021 PDF ICCV 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Semantic Segmentation GAMUS ShapeConv mIoU 55.86 # 5
Semantic Segmentation LLRGBD-synthetic ShapeConv (ResNeXt-101) mIoU 63.26 # 6
Semantic Segmentation NYU Depth v2 ShapeConv (ResNet-101) Mean IoU 49.0% # 61
Semantic Segmentation NYU Depth v2 ShapeConv (ResNext-101) Mean IoU 51.3% # 39
Semantic Segmentation NYU Depth v2 ShapeConv (ResNet-50) Mean IoU 48.8% # 64
Thermal Image Segmentation RGB-T-Glass-Segmentation ShapeConv MAE 0.054 # 12
Semantic Segmentation Stanford2D3D - RGBD ShapeConv-101 mIoU 60.6 # 3
mAcc 70.0 # 1
Pixel Accuracy 82.7 # 1
Semantic Segmentation SUN-RGBD PSD-ResNet50 Mean IoU 48.6% # 20