Training-Free Affordance Labeling and Exploration Using Subspace Projection and Manifold Curvature Over Pre-Trained Deep Networks

Training-Free Affordance Labeling and Exploration Using Subspace Projection and Manifold Curvature Over Pre-Trained Deep Networks

The advancement in computing power has significantly reduced the training times for deep learning, enabling the rapid development of networks designed for object recognition. However, the exploration of object utility, the object’s affordance, as opposed to object recognition, has receive...

Full description

Saved in:
Bibliographic Details
Main Authors: Ismail Ozcil, A. Bugra Koku
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Affordance
deep learning
manifold curvature
subspace clustering
Online Access:https://ieeexplore.ieee.org/document/10979846/
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://ieeexplore.ieee.org/document/10979846/

Similar Items