DeepAI AI Chat
Log In Sign Up

Masked Supervised Learning for Semantic Segmentation

by   H. Zunair, et al.

Self-attention is of vital importance in semantic segmentation as it enables modeling of long-range context, which translates into improved performance. We argue that it is equally important to model short-range context, especially to tackle cases where not only the regions of interest are small and ambiguous, but also when there exists an imbalance between the semantic classes. To this end, we propose Masked Supervised Learning (MaskSup), an effective single-stage learning paradigm that models both short- and long-range context, capturing the contextual relationships between pixels via random masking. Experimental results demonstrate the competitive performance of MaskSup against strong baselines in both binary and multi-class segmentation tasks on three standard benchmark datasets, particularly at handling ambiguous regions and retaining better segmentation of minority classes with no added inference cost. In addition to segmenting target regions even when large portions of the input are masked, MaskSup is also generic and can be easily integrated into a variety of semantic segmentation methods. We also show that the proposed method is computationally efficient, yielding an improved performance by 10% on the mean intersection-over-union (mIoU) while requiring 3× less learnable parameters.


page 2

page 4

page 8

page 9

page 10


CTNet: Context-based Tandem Network for Semantic Segmentation

Contextual information has been shown to be powerful for semantic segmen...

SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation

Capturing global contextual representations by exploiting long-range pix...

Attention on Classification for Fire Segmentation

Detection and localization of fire in images and videos are important in...

Rethinking Learnable Tree Filter for Generic Feature Transform

The Learnable Tree Filter presents a remarkable approach to model struct...

Capturing Omni-Range Context for Omnidirectional Segmentation

Convolutional Networks (ConvNets) excel at semantic segmentation and hav...

EurNet: Efficient Multi-Range Relational Modeling of Spatial Multi-Relational Data

Modeling spatial relationship in the data remains critical across many d...

Class Based Thresholding in Early Exit Semantic Segmentation Networks

We propose Class Based Thresholding (CBT) to reduce the computational co...