scholarly journals Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection

2019 ◽  
Author(s):  
Taekyung Kim ◽  
Minki Jeong ◽  
Seunghyeon Kim ◽  
Seokeon Choi ◽  
Changick Kim
Keyword(s):  
Object Detection ◽  
Representation Learning ◽  
Learning Paradigm ◽  
Adaptive Representation

scholarly journals CoLR: Classification-Oriented Local Representation for Image Recognition

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-17 ◽  
Author(s):  
Tan Guo ◽  
Lei Zhang ◽  
Xiaoheng Tan ◽  
Liu Yang ◽  
Zhiwei Guo ◽  
...  
Keyword(s):  
Image Recognition ◽  
Representation Learning ◽  
Test Sample ◽  
Local Representation ◽  
Adaptive Representation ◽  
Augmented Lagrange Multiplier ◽  
Face Datasets ◽  
Core Idea ◽  
Object Features ◽  
Fully Connected

Naïve sparse representation has stability problem due to its unsupervised nature, which is not preferred for classification tasks. For this problem, this paper presents a novel representation learning method named classification-oriented local representation (CoLR) for image recognition. The core idea of CoLR is to find the most relevant training classes and samples with test sample by taking the merits of class-wise sparseness weighting, sample locality, and label prior. The proposed representation strategy can not only promote a classification-oriented representation, but also boost a locality adaptive representation within the selected training classes. The CoLR model is efficiently solved by Augmented Lagrange Multiplier (ALM) scheme based on a variable splitting strategy. Then, the performance of the proposed model is evaluated on benchmark face datasets and deep object features. Specifically, the deep features of the object dataset are obtained by a well-trained convolutional neural network (CNN) with five convolutional layers and three fully connected layers on the challenging ImageNet. Extensive experiments verify the superiority of CoLR in comparison with some state-of-the-art models.

scholarly journals Domain adaptive representation learning for facial action unit recognition

2020 ◽  
Vol 102 ◽  
pp. 107127 ◽  
Author(s):  
Nishant Sankaran ◽  
Deen Dayal Mohan ◽  
Nagashri N. Lakshminarayana ◽  
Srirangaraj Setlur ◽  
Venu Govindaraju
Keyword(s):  
Representation Learning ◽  
Action Unit ◽  
Facial Action ◽  
Adaptive Representation

The Effect of Outcome Probability on Generalization in Predictive Learning

2019 ◽  
Vol 66 (1) ◽  
pp. 23-39 ◽  
Author(s):  
Hadar Ram ◽  
Dieter Struyf ◽  
Bram Vervliet ◽  
Gal Menahem ◽  
Nira Liberman
Keyword(s):  
High Probability ◽  
Lower Probability ◽  
Perceptual Similarity ◽  
Learning Paradigm ◽  
Predictive Learning ◽  
Lightning Bolt ◽  
Outcome Probability

Abstract. People apply what they learn from experience not only to the experienced stimuli, but also to novel stimuli. But what determines how widely people generalize what they have learned? Using a predictive learning paradigm, we examined the hypothesis that a low (vs. high) probability of an outcome following a predicting stimulus would widen generalization. In three experiments, participants learned which stimulus predicted an outcome (S+) and which stimulus did not (S−) and then indicated how much they expected the outcome after each of eight novel stimuli ranging in perceptual similarity to S+ and S−. The stimuli were rings of different sizes and the outcome was a picture of a lightning bolt. As hypothesized, a lower probability of the outcome widened generalization. That is, novel stimuli that were similar to S+ (but not to S−) produced expectations for the outcome that were as high as those associated with S+.

Sign in / Sign up

Export Citation Format

Share Document