Semantic SuperPoint: A Deep Semantic Descriptor

11/02/2022
by   Gabriel S. Gama, et al.
0

Several SLAM methods benefit from the use of semantic information. Most integrate photometric methods with high-level semantics such as object detection and semantic segmentation. We propose that adding a semantic segmentation decoder in a shared encoder architecture would help the descriptor decoder learn semantic information, improving the feature extractor. This would be a more robust approach than only using high-level semantic information since it would be intrinsically learned in the descriptor and would not depend on the final quality of the semantic prediction. To add this information, we take advantage of multi-task learning methods to improve accuracy and balance the performance of each task. The proposed models are evaluated according to detection and matching metrics on the HPatches dataset. The results show that the Semantic SuperPoint model performs better than the baseline one.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/18/2020

A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection

Both high-level and high-resolution feature representations are of great...
research
01/12/2019

Real-time Joint Object Detection and Semantic Segmentation Network for Automated Driving

Convolutional Neural Networks (CNN) are successfully used for various vi...
research
01/12/2018

Prototypicality effects in global semantic description of objects

We propose a new approach to face the semantic features descriptions of ...
research
02/08/2022

Wireless Transmission of Images With The Assistance of Multi-level Semantic Information

Semantic-oriented communication has been considered as a promising to bo...
research
02/21/2023

Non-pooling Network for medical image segmentation

Existing studies tend tofocus onmodel modifications and integration with...
research
09/15/2022

PROB-SLAM: Real-time Visual SLAM Based on Probabilistic Graph Optimization

Traditional SLAM algorithms are typically based on artificial features, ...
research
01/26/2023

Semantic Segmentation Enhanced Transformer Model for Human Attention Prediction

Saliency Prediction aims to predict the attention distribution of human ...

Please sign up or login with your details

Forgot password? Click here to reset