Deep Image Annotation and Classification by Fusing Multi-Modal Semantic Topics

doi:10.3837/tiis.2018.01.019

Cited by 2 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the that maximizes this marginal likelihood, the distribution of the function value for the unobserved data is . That is, the posterior distribution has mean function and variance function , where and are calculated through the following equations: (9) where, denotes the covariance values between all observed data and the new data based on the hyperparameter value , and is the variance value at . Fig.…”

Section: Gaussian Process Regressionmentioning

confidence: 99%

Adversarial Detection with Gaussian Process Regression-based Detector

2019

KSII TIIS

View full text Add to dashboard Cite

Adversarial attack is a technique that causes a malfunction of classification models by adding noise that cannot be distinguished by humans, which poses a threat to a deep learning model. In this paper, we propose an efficient method to detect adversarial images using Gaussian process regression. Existing deep learning-based adversarial detection methods require numerous adversarial images for their training. The proposed method overcomes this problem by performing classification based on the statistical features of adversarial images and clean images that are extracted by Gaussian process regression with a small number of images. This technique can determine whether the input image is an adversarial image by applying Gaussian process regression based on the intermediate output value of the classification model. Experimental results show that the proposed method achieves higher detection performance than the other deep learning-based adversarial detection methods for powerful attacks. In particular, the Gaussian process regression-based detector shows better detection performance than the baseline models for most attacks in the case with fewer adversarial examples.

show abstract

Section: Gaussian Process Regressionmentioning

confidence: 99%

Adversarial Detection with Gaussian Process Regression-based Detector

2019

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…Previously methods build image annotation model based on three basic dependencies: relations between image and label (image/label), between images (image/image) and between labels (label/label). Assuming targets are independent to each other, they managed to establish the relations between images and labels [1][2][3][4][5][6][7][8]. Despite its powerful discriminative ability, it cannot detect those visually hard-to-detect targets, such as small and blured objects.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Attention Annotation Model: Optimizing the Prediction Path through Dependency Fusion

2019

KSII TIIS

View full text Add to dashboard Cite

Previous methods build image annotation model by leveraging three basic dependencies: relations between image and label (image/label), between images (image/image) and between labels (label/label). Even though plenty of researches show that multiple dependencies can work jointly to improve annotation performance, different dependencies actually do not "work jointly" in their diagram, whose performance is largely depending on the result predicted by image/label section. To address this problem, we propose the adaptive attention annotation model (AAAM) to associate these dependencies with the prediction path, which is composed of a series of labels (tags) in the order they are detected. In particular, we optimize the prediction path by detecting the relevant labels from the easy-to-detect to the hard-to-detect, which are found using Binary Cross-Entropy (BCE) and Triplet Margin (TM) losses, respectively. Besides, in order to capture the inforamtion of each label, instead of explicitly extracting regional featutres, we propose the self-attention machanism to implicitly enhance the relevant region and restrain those irrelevant. To validate the effective of the model, we conduct experiments on three well-known public datasets, COCO 2014, IAPR TC-12 and NUSWIDE, and achieve better performance than the state-of-the-art methods.

show abstract

Deep Image Annotation and Classification by Fusing Multi-Modal Semantic Topics

Cited by 2 publications

References 37 publications

Adversarial Detection with Gaussian Process Regression-based Detector

Adversarial Detection with Gaussian Process Regression-based Detector

Adaptive Attention Annotation Model: Optimizing the Prediction Path through Dependency Fusion

Contact Info

Product

Resources

About