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

11/03/2021
by   Shubhankar Borse, et al.
0

While deeply supervised networks are common in recent literature, they typically impose the same learning objective on all transitional layers despite their varying representation powers. In this paper, we propose Hierarchically Supervised Semantic Segmentation (HS3), a training scheme that supervises intermediate layers in a segmentation network to learn meaningful representations by varying task complexity. To enforce a consistent performance vs. complexity trade-off throughout the network, we derive various sets of class clusters to supervise each transitional layer of the network. Furthermore, we devise a fusion framework, HS3-Fuse, to aggregate the hierarchical features generated by these layers, which can provide rich semantic contexts and further enhance the final segmentation. Extensive experiments show that our proposed HS3 scheme considerably outperforms vanilla deep supervision with no added inference cost. Our proposed HS3-Fuse framework further improves segmentation predictions and achieves state-of-the-art results on two large segmentation benchmarks: NYUD-v2 and Cityscapes.

READ FULL TEXT

page 1

page 2

page 6

page 10

research
12/30/2019

Discovering Latent Classes for Semi-Supervised Semantic Segmentation

High annotation costs are a major bottleneck for the training of semanti...
research
07/15/2020

ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning

The state of the art in semantic segmentation is steadily increasing in ...
research
07/13/2022

SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision

Accurate semantic segmentation models typically require significant comp...
research
08/04/2021

Specialize and Fuse: Pyramidal Output Representation for Semantic Segmentation

We present a novel pyramidal output representation to ensure parsimony w...
research
02/19/2021

Scribble-Supervised Semantic Segmentation by Uncertainty Reduction on Neural Representation and Self-Supervision on Neural Eigenspace

Scribble-supervised semantic segmentation has gained much attention rece...
research
12/09/2020

AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentation

In this paper, we present an Assertion-based Multi-View Fusion network (...
research
11/23/2019

On Symbiosis of Attribute Prediction and Semantic Segmentation

In this paper, we propose to employ semantic segmentation to improve per...

Please sign up or login with your details

Forgot password? Click here to reset