Compound Projection Learning for Bridging Seen and Unseen Objects

2022 ◽  
pp. 1-1
Author(s):  
Wenli Song ◽  
Lei Zhang ◽  
Xinbo Gao
Keyword(s):  
2021 ◽  
Author(s):  
Ning Mei ◽  
Roberto Santana ◽  
David Soto

AbstractDespite advances in the neuroscience of visual consciousness over the last decades, we still lack a framework for understanding the scope of unconscious processing and how it relates to conscious experience. Previous research observed brain signatures of unconscious contents in visual cortex, but these have not been identified in a reliable manner, with low trial numbers and signal detection theoretic constraints not allowing to decisively discard conscious perception. Critically, the extent to which unconscious content is represented in high-level processing stages along the ventral visual stream and linked prefrontal areas remains unknown. Using a within-subject, high-precision, highly-sampled fMRI approach, we show that unconscious contents, even those associated with null sensitivity, can be reliably decoded from multivoxel patterns that are highly distributed along the ventral visual pathway and also involving prefrontal substrates. Notably, the neural representation in these areas generalised across conscious and unconscious visual processing states, placing constraints on prior findings that fronto-parietal substrates support the representation of conscious contents and suggesting revisions to models of consciousness such as the neuronal global workspace. We then provide a computational model simulation of visual information processing/representation in the absence of perceptual sensitivity by using feedforward convolutional neural networks trained to perform a similar visual task to the human observers. The work provides a novel framework for pinpointing the neural representation of unconscious knowledge across different task domains.


2021 ◽  
Author(s):  
Ruiqi Li ◽  
Hua Hua ◽  
Patrik Haslum ◽  
Jochen Renz

Detecting, characterizing and adapting to novelty, whether in the form of previously unseen objects or phenomena, or unexpected changes in the behavior of known elements, is essential for Artificial Intelligence agents to operate reliably in unconstrained real-world environments. We propose an automatic, unsupervised approach to novelty characterization for dynamic domains, based on describing the behaviors and interactions of objects in terms of their possible actions. To abstract from the variety of realizations of an action that can occur in physical domains, we model states in terms of qualitative spatial relations (QSRs) between their entities. By first learning a model of actions in the non-novel environment from the state transitions observed as the agent interacts with the world, we can detect novelty by the persistent deviations from this model that it causes, and characterize the novelty by new or modified actions. We also present a new method of learning action models from observation, based on conceptual similarity and hierarchical clustering.


Sensors ◽  
2019 ◽  
Vol 19 (3) ◽  
pp. 523 ◽  
Author(s):  
Brayan Zapata-Impata ◽  
Pablo Gil ◽  
Fernando Torres

Robotic manipulators have to constantly deal with the complex task of detecting whether a grasp is stable or, in contrast, whether the grasped object is slipping. Recognising the type of slippage—translational, rotational—and its direction is more challenging than detecting only stability, but is simultaneously of greater use as regards correcting the aforementioned grasping issues. In this work, we propose a learning methodology for detecting the direction of a slip (seven categories) using spatio-temporal tactile features learnt from one tactile sensor. Tactile readings are, therefore, pre-processed and fed to a ConvLSTM that learns to detect these directions with just 50 ms of data. We have extensively evaluated the performance of the system and have achieved relatively high results at the detection of the direction of slip on unseen objects with familiar properties (82.56% accuracy).


2015 ◽  
Vol 35 (8) ◽  
pp. 959-976 ◽  
Author(s):  
Marek Kopicki ◽  
Renaud Detry ◽  
Maxime Adjigble ◽  
Rustam Stolkin ◽  
Ales Leonardis ◽  
...  

This paper presents a method for one-shot learning of dexterous grasps and grasp generation for novel objects. A model of each grasp type is learned from a single kinesthetic demonstration and several types are taught. These models are used to select and generate grasps for unfamiliar objects. Both the learning and generation stages use an incomplete point cloud from a depth camera, so no prior model of an object shape is used. The learned model is a product of experts, in which experts are of two types. The first type is a contact model and is a density over the pose of a single hand link relative to the local object surface. The second type is the hand-configuration model and is a density over the whole-hand configuration. Grasp generation for an unfamiliar object optimizes the product of these two model types, generating thousands of grasp candidates in under 30 seconds. The method is robust to incomplete data at both training and testing stages. When several grasp types are considered the method selects the highest-likelihood grasp across all the types. In an experiment, the training set consisted of five different grasps and the test set of 45 previously unseen objects. The success rate of the first-choice grasp is 84.4% or 77.7% if seven views or a single view of the test object are taken, respectively.


PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0244968
Author(s):  
Elena Luchkina ◽  
Sandra R. Waxman

Human language permits us to call to mind objects, events, and ideas that we cannot witness directly. This capacity rests upon abstract verbal reference: the appreciation that words are linked to mental representations that can be established, retrieved and modified, even when the entities to which a word refers is perceptually unavailable. Although establishing verbal reference is a pivotal achievement, questions concerning its developmental origins remain. To address this gap, we investigate infants’ ability to establish a representation of an object, hidden from view, from language input alone. In two experiments, 15-month-olds (N = 72) and 12-month-olds (N = 72) watch as an actor names three familiar, visible objects; she then provides a novel name for a fourth, hidden fully from infants’ view. In the Semantic Priming condition, the visible familiar objects all belong to the same semantic neighborhood (e.g., apple, banana, orange). In the No Priming condition, the objects are drawn from different semantic neighborhoods (e.g., apple, shoe, car). At test infants view two objects. If infants can use the naming information alone to identify the likely referent, then infants in the Semantic Priming, but not in the No Priming condition, will successfully infer the referent of the fourth (hidden) object. Brief summary of results here. Implications for the development of abstract verbal reference will be discussed.


i-Perception ◽  
2016 ◽  
Vol 7 (4) ◽  
pp. 204166951666453 ◽  
Author(s):  
Simon J. Hazenberg ◽  
Rob van Lier

1996 ◽  
Vol 173 ◽  
pp. 215-220 ◽  
Author(s):  
C. Alard

The DUO (Disk Unseen Objects) program is a project with the main goal of searching for galactic dark matter in a field towards the Galactic Bulge (Alard et al. 1995b). In this paper I present the results obtained from the analysis of half of the data collected during the 1994 season. I start with a brief description of the DUO project, and I will continue with an analysis of the microlensing candidates that I found. In all I found 13 microlensing events in the DUO data, including a double lens event. A model of the double lens light curve predicts a blending effect. The presence of the blended component was confirmed by a gravity center shift during the event. Taking into account the model prediction and the shift, we could predict the exact geometry of the blend. This prediction was recently confirmed by direct imaging of the blend under good seeing conditions. The durations of the single lens events are quite short, but the durations can be seriously affected by blending. I propose a simple experimental test to quantify this duration bias. In the conclusion I emphasize the great importance of a good knowledge of the inner Galactic structure to get a reliable quantitative description of microlensing towards the bulge. Finally I will show that the large number of variables stars found in the data could be a powerful tool to probe this structure.


2018 ◽  
Vol 6 ◽  
pp. 133-144 ◽  
Author(s):  
Guillem Collell ◽  
Marie-Francine Moens

Spatial understanding is crucial in many real-world problems, yet little progress has been made towards building representations that capture spatial knowledge. Here, we move one step forward in this direction and learn such representations by leveraging a task consisting in predicting continuous 2D spatial arrangements of objects given object-relationship-object instances (e.g., “cat under chair”) and a simple neural network model that learns the task from annotated images. We show that the model succeeds in this task and, furthermore, that it is capable of predicting correct spatial arrangements for unseen objects if either CNN features or word embeddings of the objects are provided. The differences between visual and linguistic features are discussed. Next, to evaluate the spatial representations learned in the previous task, we introduce a task and a dataset consisting in a set of crowdsourced human ratings of spatial similarity for object pairs. We find that both CNN (convolutional neural network) features and word embeddings predict human judgments of similarity well and that these vectors can be further specialized in spatial knowledge if we update them when training the model that predicts spatial arrangements of objects. Overall, this paper paves the way towards building distributed spatial representations, contributing to the understanding of spatial expressions in language.


Sign in / Sign up

Export Citation Format

Share Document