Affordance Labeling and Exploration: A Manifold-Based Approach
Authors:
- İsmail ÖzçilIÖİsmail Özçil
- A. Buğra KokuAKA. Buğra Koku
Preprint
Abstract
The advancement in computing power has significantly reduced the training times for deep learning, fostering the rapid development of networks designed for object recognition. However, the exploration of object utility, which is the affordance of the object, as opposed to object recognition, has received comparatively less attention. This work focuses on the problem of exploration of object affordances using existing networks trained on the object classification dataset. While pre-trained networks have proven to be instrumental in transfer learning for classification tasks, this work diverges from conventional object classification methods. Instead, it employs pre-trained networks to discern affordance labels without the need for specialized layers, abstaining from modifying the final layers through the addition of classification layers. To facilitate the determination of affordance labels without such modifications, two approaches, i.e. subspace clustering and manifold curvature methods are tested. These methods offer a distinct perspective on affordance label recognition. Especially, manifold curvature method has been successfully tested with nine distinct pre-trained networks, each achieving an accuracy exceeding 95%. Moreover, it is observed that manifold curvature and subspace clustering methods explore affordance labels that are not marked in the ground truth, but object affords in various cases.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Hardware-Aware Affordance Detection for Application in Portable Embedded SystemsIEEE Access, 2021
- Joint Object Affordance Reasoning and Segmentation in RGB-D VideosIEEE Access, 2021
- Looking to recognise: the pre-eminence of semantic over sensorimotor processing in human tool useScientific Reports, 2020
- A New Localization Objective for Accurate Fine-Grained Affordance Segmentation Under High-Scale VariationsIEEE Access, 2019
- Learning to Act Properly: Predicting and Explaining Affordances from Images2018
- A Highway-Driving System Design Viewpoint Using an Agent-Based Modeling of an Affordance-Based Finite State AutomataIEEE Access, 2017
- Aggregated Residual Transformations for Deep Neural Networks2017
- Deep Residual Learning for Image Recognition2016
- The initial development of object knowledge by a learning robotRobotics and Autonomous Systems, 2008
- Cognitive, physical, sensory, and functional affordances in interaction designBehaviour & Information Technology, 2003