Vision: are models of object recognition catching up with the brain?
Tomaso Poggio,Shimon Ullman +1 more
Reads0
Chats0
TLDR
The ongoing struggle of visual models to catch up with the visual cortex is discussed, key reasons for the relatively rapid improvement of artificial systems and models are identified, and open problems for computational vision in this domain are identified.Abstract:
Object recognition has been a central yet elusive goal of computational vision. For many years, computer performance seemed highly deficient and unable to emulate the basic capabilities of the human recognition system. Over the past decade or so, computer scientists and neuroscientists have developed algorithms and systems-and models of visual cortex-that have come much closer to human performance in visual identification and categorization. In this personal perspective, we discuss the ongoing struggle of visual models to catch up with the visual cortex, identify key reasons for the relatively rapid improvement of artificial systems and models, and identify open problems for computational vision in this domain.read more
Citations
More filters
Journal ArticleDOI
From the phenomenology to the mechanisms of consciousness: Integrated Information Theory 3.0.
TL;DR: Integrated Information Theory of consciousness 3.0 is presented, which incorporates several advances over previous formulations and arrives at an identity: an experience is a maximally irreducible conceptual structure (MICS, a constellation of concepts in qualia space), and the set of elements that generates it constitutes a complex.
Journal ArticleDOI
Segmentation and Image Analysis of Abnormal Lungs at CT: Current Approaches, Challenges, and Future Trends
Awais Mansoor,Ulas Bagci,Brent Foster,Ziyue Xu,Georgios Z. Papadakis,Les R. Folio,Jayaram K. Udupa,Daniel J. Mollura +7 more
TL;DR: A critical summary of the current methods for lung segmentation on CT images is provided, with special emphasis on the accuracy and performance of the methods in cases with abnormalities and cases with exemplary pathologic findings.
Journal ArticleDOI
Attention Reduces Spatial Uncertainty in Human Ventral Temporal Cortex
TL;DR: It is found that attention to the stimulus systematically and selectively modulates responses in VTC, but not early visual areas, and a population receptive field model of spatial responses in human VTC is developed.
Journal ArticleDOI
The structure of reinforcement-learning mechanisms in the human brain
TL;DR: Evidence for the distinction between model-based and model-free reinforcement-learning and their arbitration, and the possibility of integrating across these different domains as a means of gaining a more complete understanding of how the brain learns from reinforcement are evaluated.
Journal ArticleDOI
Feature integration and object representations along the dorsal stream visual hierarchy.
Carolyn J. Perry,Mazyar Fallah +1 more
TL;DR: This work reviews the hierarchical processing of motion along the dorsal stream and the building up of object representations along the ventral stream, and proposes a framework describing how and at what stage different features are integrated into dorsal visual stream object representations.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Statistical learning theory
TL;DR: Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
Journal ArticleDOI
A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
Yoav Freund,Robert E. Schapire +1 more
TL;DR: The model studied can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting, and it is shown that the multiplicative weight-update Littlestone?Warmuth rule can be adapted to this model, yielding bounds that are slightly weaker in some cases, but applicable to a considerably more general class of learning problems.