A-LINK: Recognizing Disguised Faces via Active Learning based Inter-Domain Knowledge
Citations
5 citations
Cites background from "A-LINK: Recognizing Disguised Faces..."
...In the worst case, these changes are made intentionally to hide ones identity or imitate the appearance of another person [15, 38, 47]....
[...]
2 citations
Cites background or methods from "A-LINK: Recognizing Disguised Faces..."
...Compared to A-LINK [28], an average absolute increase of 2....
[...]
...Models trained with A2-LINK even outperform A-LINK [28] by a significant margin, thus reinforcing...
[...]
...(A-LINK [28]) give a reasonably good increase in performance, both when dealing with disguise and multiresolution as covariates....
[...]
...2A shorter version of the manuscript was presented at IEEE International Conference on BTAS, 2019 [28]....
[...]
...This paper builds on top of A-LINK2 [28] and introduces an adversarial noise component while constructing hybrid noise inputs for the algorithm....
[...]
References
5,742 citations
5,227 citations
"A-LINK: Recognizing Disguised Faces..." refers methods in this paper
...Entropy Sampling: selects data instances based on entropy; Shanon entropy over all classes [20]....
[...]
3,212 citations
"A-LINK: Recognizing Disguised Faces..." refers methods in this paper
...Work on estimating distances of points from decision boundaries using adversarial perturbations [4] is inspired by work that queries points in an SVM [27]....
[...]
2,784 citations
"A-LINK: Recognizing Disguised Faces..." refers background in this paper
...propose a model-weight based ensemble technique which trains student and teacher models together, yielding near state-of-the-art performance with a fraction of labelled data [26]....
[...]
2,226 citations
"A-LINK: Recognizing Disguised Faces..." refers background in this paper
...pling [12] selects points for which a given model is least confident about its predictions....
[...]