paper-with-me

Papers

Segmenting Object Affordances: Reproducibility and Sensitivity to Scale

2024-09-03 · Tommaso Apicella, Alessio Xompero, Paolo Gastaldo, Andrea Cavallaro

Visual affordance segmentation identifies image regions of an object an agent can interact with. Existing methods re-use and adapt learning-based architectures for semantic segmentation to the affordance segmentation task and evaluate on small-size datasets. However, experimental setups are often not reproducible, thus leading to unfair and inconsistent comparisons. In this work, we benchmark these methods under a reproducible setup on two single objects scenarios, tabletop without occlusions and hand-held containers, to facilitate future comparisons. We include a version of a recent architecture, Mask2Former, re-trained for affordance segmentation and show that this model is the best-performing on most testing sets of both scenarios. Our analysis shows that models are not robust to scale variations when object resolutions differ from those in the training set.

📄 PDF Abstract BibTeX arXiv:2409.01814

Code (1)

apicis/aff-seg 공식 구현 pytorch

Tasks

ObjectSegmentationSemantic SegmentationSensitivity

Similar Papers 제목 키워드 기반

Visual Affordances: Enabling Robots to Understand Object Functionality

2025-05-08 · Tommaso Apicella, Alessio Xompero, Andrea Cavallaro

Human-robot interaction for assistive technologies relies on the prediction of affordances, which are the potential actions a robot can perform on objects. Predicting object affordances from visual perception is formulat…

ObjectPrediction

A Deep Learning Approach to Object Affordance Segmentation

2020-04-18 · Spyridon Thermos, Petros Daras, Gerasimos Potamianos

Learning to understand and infer object functionalities is an important step towards robust visual intelligence. Significant research efforts have recently focused on segmenting the object parts that enable specific type…

Deep LearningHuman-Object Interaction DetectionObjectobject-detection+2

Binge Watching: Scaling Affordance Learning from Sitcoms

2018-04-09 · CVPR 2017 7 · Xiaolong Wang, Rohit Girdhar, Abhinav Gupta

In recent years, there has been a renewed interest in jointly modeling perception and action. At the core of this investigation is the idea of modeling affordances(Affordances are opportunities of interaction in the scen…

Video models are zero-shot learners and reasoners

2025-09-24 · Thaddäus Wiedemer, Yuxuan Li, Paul Vicol, Shixiang Shane Gu 외 arxiv

The remarkable zero-shot capabilities of Large Language Models (LLMs) have propelled natural language processing from task-specific models to unified, generalist foundation models. This transformation emerged from simple…

Visual Reasoning

Multi-Object Graph Affordance Network: Goal-Oriented Planning through Learned Compound Object Affordances

2023-09-19 · Tuba Girgin, Emre Ugur

Learning object affordances is an effective tool in the field of robot learning. While the data-driven models investigate affordances of single or paired objects, there is a gap in the exploration of affordances of compo…

Object