DeepAI AI Chat
Log In Sign Up

Specialize and Fuse: Pyramidal Output Representation for Semantic Segmentation

by   Chi-Wei Hsiao, et al.
National Tsing Hua University

We present a novel pyramidal output representation to ensure parsimony with our "specialize and fuse" process for semantic segmentation. A pyramidal "output" representation consists of coarse-to-fine levels, where each level is "specialize" in a different class distribution (e.g., more stuff than things classes at coarser levels). Two types of pyramidal outputs (i.e., unity and semantic pyramid) are "fused" into the final semantic output, where the unity pyramid indicates unity-cells (i.e., all pixels in such cell share the same semantic label). The process ensures parsimony by predicting a relatively small number of labels for unity-cells (e.g., a large cell of grass) to build the final semantic output. In addition to the "output" representation, we design a coarse-to-fine contextual module to aggregate the "features" representation from different levels. We validate the effectiveness of each key module in our method through comprehensive ablation studies. Finally, our approach achieves state-of-the-art performance on three widely-used semantic segmentation datasets – ADE20K, COCO-Stuff, and Pascal-Context.


page 2

page 4

page 8

page 11

page 14

page 15


Class-wise Dynamic Graph Convolution for Semantic Segmentation

Recent works have made great progress in semantic segmentation by exploi...

S^2-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation

Modern high-performance semantic segmentation methods employ a heavy bac...

Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU

The state-of-the-art object detection and image classification methods c...

Combining the Best of Graphical Models and ConvNets for Semantic Segmentation

We present a two-module approach to semantic segmentation that incorpora...

HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation

While deeply supervised networks are common in recent literature, they t...

Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing

Human parsing, or human body part semantic segmentation, has been an act...

Semantic Segmentation via Highly Fused Convolutional Network with Multiple Soft Cost Functions

Semantic image segmentation is one of the most challenged tasks in compu...