Related Experiment Video
Updated: May 16, 2025
12:08
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
Published on: August 13, 2014
24.5K
AESeg: Affinity-enhanced segmenter using feature class mapping knowledge distillation for efficient RGB-D semantic
Wujie Zhou1, Yuxiang Xiao2, Fangfang Qiang2
1School of Information & Electronic Engineering, Zhejiang University of Science & Technology, Hangzhou 310023, China; School of Computer Science and Engineering, Nanyang Technological University, Singapore 308232, Singapore.
Summary
This study introduces an affinity-enhanced semantic segmentation framework, combining static and dynamic methods. It achieves high accuracy comparable to dynamic approaches with significantly reduced computational cost for deep learning models.
Area of Science:
- Computer Vision
- Deep Learning
- Artificial Intelligence
Background:
- Dynamic semantic segmentation models offer high accuracy but incur significant computational costs.
- Static segmentation methods, like fully convolutional networks, are computationally efficient but lack global semantic awareness.
Purpose of the Study:
- To develop an efficient semantic segmentation framework that combines the accuracy of dynamic methods with the computational efficiency of static methods.
- To reduce the computational burden associated with learning and inferring class embeddings in dynamic segmentation.
Main Methods:
- Proposed an affinity-enhanced semantic segmentation framework integrating static and dynamic methodologies.
- Constructed a binary affinity matrix encoding pixel-wise category relationships to act as a dynamic classification kernel.
- Introduced a feature-to-category mapping refinement technique for improved accuracy without increased complexity.
Main Results:
- The proposed method achieved performance comparable to purely dynamic approaches with substantially reduced computational overhead.
- Demonstrated state-of-the-art performance on the NYUv2 and SUN-RGBD datasets.
- Verified effectiveness across diverse scenes, including outdoor environments on the CamVid dataset.
Conclusions:
- The affinity-enhanced framework offers a computationally efficient yet accurate solution for semantic segmentation.
- The feature-to-category mapping refinement effectively enhances segmentation accuracy.
- The proposed method represents a significant advancement in deep learning for semantic segmentation.
