2020
DOI: 10.1016/j.patcog.2020.107263
|View full text |Cite
|
Sign up to set email alerts
|

Guided CNN for generalized zero-shot and open-set recognition using visual and semantic prototypes

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
14
0

Year Published

2020
2020
2025
2025

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 34 publications
(14 citation statements)
references
References 10 publications
0
14
0
Order By: Relevance
“…The second-level soft attention α is computed by using J matrix and K network similar to the first part (P I) of (2) i.e., α = softmax(tanh(J W B )W A ), where W B and W A are learned parameters of K network. The feature embedding F2 ∈ R r×m is constructed by summation of F1 and F 1 = α F1 as (3). Note that, since the information of the most relevant attribute to a region is propagated into the second-level and beyond through the embedding F1 , we do not use {T i } r i=1 neural networks in the second-level.…”
Section: Attribute Guided Attention Networkmentioning
confidence: 99%
See 1 more Smart Citation
“…The second-level soft attention α is computed by using J matrix and K network similar to the first part (P I) of (2) i.e., α = softmax(tanh(J W B )W A ), where W B and W A are learned parameters of K network. The feature embedding F2 ∈ R r×m is constructed by summation of F1 and F 1 = α F1 as (3). Note that, since the information of the most relevant attribute to a region is propagated into the second-level and beyond through the embedding F1 , we do not use {T i } r i=1 neural networks in the second-level.…”
Section: Attribute Guided Attention Networkmentioning
confidence: 99%
“…Though, the underlying distribution of source and target domains is disjoint, the ZSL setting assumes that the trained visual classifier knows whether a test sample belongs to a source or target class. To alleviate such an unrealistic assumption, the ZSL setting is extended to a more realistic setting called Generalized Zero-Shot Learning (GZSL) [2,3,4], where the classifier has to classify test images from both source and target classes. The ultimate aim of this work is to improve GZSL for fine-grained recognition.…”
Section: Introductionmentioning
confidence: 99%
“…LATEM [24] embedded the visual features with a piecewise linear function which was trained by a ranking based objective function. To alleviate the hubness problem [1] in the visual-to-semantic embedding methods, some works [2,31,32,33] proposed to learn a semantic-to-visual embedding, where they mapped semantic features into visual features by a regression function. DEM [1] used a two-layer neural network to learn a discriminative visual features space from the semantic feature space.…”
Section: Zero-shot Learningmentioning
confidence: 99%
“…Outliers are usually rejected by thresholding some kind of score. Distance based classifiers classify a sample as an outlier if it is far from any of the learned prototypes [15].…”
Section: Open-set Recognitionmentioning
confidence: 99%