2017 · 91 citations · 39 references
ComputingRobotics EngineeringComputer VisionMachine VisionRobot VisionImage AnnotationInstance SegmentationObject DetectionRobotic VisionScene UnderstandingSemantic SegmentationAffordance DetectionAffordancesConvolutional Neural NetworksKeypoint DetectionVisual Scene UnderstandingWeak SupervisionWeakly Supervised LearningWeakly Supervised Segmentation
Localizing functional regions of objects or affordances is an important aspect of scene understanding and relevant for many robotics applications. In this work, we introduce a pixel-wise annotated affordance dataset of 3090 images containing 9916 object instances. Since parts of an object can have multiple affordances, we address this by a convolutional neural network for multilabel affordance segmentation. We also propose an approach to train the network from very few keypoint annotations. Our approach achieves a higher affordance detection accuracy than other weakly supervised methods that also rely on keypoint annotations or image annotations as weak supervision.
39
Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2017 · 22.1K citations
Carsten Rother, Vladimir Kolmogorov, Andrew Blake · ACM Transactions on Graphics · 2004 · 5.8K citations · Full text
Describing objects by their attributes
Ali Farhadi, Ian Endres, Derek Hoiem et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 1.9K citations