Visual category learning can be accomplished either under ambiguous supervision or low feature saliency, but not under both challenges
نویسندگان
چکیده
منابع مشابه
Impact of feature saliency on visual category learning
People have to sort numerous objects into a large number of meaningful categories while operating in varying contexts. This requires identifying the visual features that best predict the 'essence' of objects (e.g., edibility), rather than categorizing objects based on the most salient features in a given context. To gain this capacity, visual category learning (VCL) relies on multiple cognitive...
متن کاملLabel Ranking under Ambiguous Supervision for Learning Semantic Correspondences
This paper studies the problem of learning from ambiguous supervision, focusing on the task of learning semantic correspondences. A learning problem is said to be ambiguously supervised when, for a given training input, a set of output candidates is provided with no prior of which one is correct. We propose to tackle this problem by solving a related unambiguous task with a label ranking approa...
متن کاملLearning under Distributed Weak Supervision
The availability of training data for supervision is a frequently encountered bottleneck of medical image analysis methods. While typically established by a clinical expert rater, the increase in acquired imaging data renders traditional pixel-wise segmentations less feasible. In this paper, we examine the use of a crowdsourcing platform for the distribution of super-pixel weak annotation tasks...
متن کاملOptimality of visual search under ambiguous stimuli
A hallmark of optimal decision making is that cues are weighted by their reliability. Previous studies have reported evidence for reliability weighting in several human perceptual decision-making tasks in which sensory noise was the only possible source of errors. Here we use a target detection task to test whether optimality generalizes to situations where stimulus ambiguity is an additional s...
متن کاملTowards Intelligent Visual Understanding under Minimal Supervision
Because of playing one of the most important roles in the artificial intelligent systems like robots, visual understanding has gained vast interests in the past few decades. Most of the existing approaches need human labelled training data to train the learning models for visual understanding and in the most recent years, significant performance gain was obtained relying on unparalleled tremend...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Vision
سال: 2011
ISSN: 1534-7362
DOI: 10.1167/11.11.841