Related papers: Affordance Labeling and Exploration: A Manifold-Ba…

Mobile robot platforms will increasingly be tasked with activities that involve grasping and manipulating objects in open world environments. Affordance understanding provides a robot with means to realise its goals and execute its tasks,…

Currently, task-oriented grasp detection approaches are mostly based on pixel-level affordance detection and semantic segmentation. These pixel-level approaches heavily rely on the accuracy of a 2D affordance mask, and the generated grasp…

Grounding object affordance is fundamental to robotic manipulation as it establishes the critical link between perception and action among interacting objects. However, prior works predominantly focus on predicting single-object affordance,…

Affordances represent the inherent effect and action possibilities that objects offer to the agents within a given context. From a theoretical viewpoint, affordances bridge the gap between effect and action, providing a functional…

The availability of large labeled datasets is the key component for the success of deep learning. However, annotating labels on large datasets is generally time-consuming and expensive. Active learning is a research area that addresses the…

Working with annotated data is the cornerstone of supervised learning. Nevertheless, providing labels to instances is a task that requires significant human effort. Several critical real-world applications make things more complicated…

The physical and textural attributes of objects have been widely studied for recognition, detection and segmentation tasks in computer vision.~A number of datasets, such as large scale ImageNet, have been proposed for feature learning using…

General robotic grasping systems require accurate object affordance perception in diverse open-world scenarios following human instructions. However, current studies suffer from the problem of lacking reasoning-based large-scale affordance…

In the face of difficult exploration problems in reinforcement learning, we study whether giving an agent an object-centric mapping (describing a set of items and their attributes) allow for more efficient learning. We found this problem is…

Deep convolutional neural networks (CNNs) have demonstrated remarkable success in computer vision by supervisedly learning strong visual feature representations. However, training CNNs relies heavily on the availability of exhaustive…

Inferring the affordance of an object and grasping it in a task-oriented manner is crucial for robots to successfully complete manipulation tasks. Affordance indicates where and how to grasp an object by taking its functionality into…

Visual affordance learning is a key component for robots to understand how to interact with objects. Conventional approaches in this field rely on pre-defined objects and actions, falling short of capturing diverse interactions in realworld…

Recent advances in self-supervised visual representation learning have paved the way for unsupervised methods tackling tasks such as object discovery and instance segmentation. However, discovering objects in an image with no supervision is…

Deep ConvNets have shown great performance for single-label image classification (e.g. ImageNet), but it is necessary to move beyond the single-label classification task because pictures of everyday life are inherently multi-label.…

We propose a framework to continuously learn object-centric representations for visual learning and understanding. Existing object-centric representations either rely on supervisions that individualize objects in the scene, or perform…

Robots are increasingly expected to manipulate objects in ever more unstructured environments where the object properties have high perceptual uncertainty from any single sensory modality. This directly impacts successful object…

In conventional supervised learning, a training dataset is given with ground-truth labels from a known label set, and the learned model will classify unseen instances to known labels. This paper studies a new problem setting in which there…

Unsupervised object discovery aims to localize objects in images, while removing the dependence on annotations required by most deep learning-based methods. To address this problem, we propose a fully unsupervised, bottom-up approach, for…

Multi-label image recognition is a practical and challenging task compared to single-label image classification. However, previous works may be suboptimal because of a great number of object proposals or complex attentional region…

Learning a latent embedding to understand the underlying nature of data distribution is often formulated in Euclidean spaces with zero curvature. However, the success of the geometry constraints, posed in the embedding space, indicates that…