Low-Resolution Face Recognition with Deep Convolutional Features in the Dissimilarity Space

Hernández-Durán, Mairelys; Plasencia-Calaña, Yenisel; Méndez-Vázquez, Heydi

doi:10.1007/978-3-030-01132-1_11

Cited by 6 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, researchers have begun to define dissimilarity spaces generated by deep learners. For example, in [34], a dissimilarity space was built on top of deep convolutional features, which produced a compact representation based on prototype selection methods. In addition, MeL methods were used in the dissimilarity space rather than the Euclidean distance.…”

Section: Introductionmentioning

confidence: 99%

Experiments of Image Classification Using Dissimilarity Spaces Built with Siamese Networks

Nanni

Minchio

Brahnam

et al. 2021

Sensors

View full text Add to dashboard Cite

Traditionally, classifiers are trained to predict patterns within a feature space. The image classification system presented here trains classifiers to predict patterns within a vector space by combining the dissimilarity spaces generated by a large set of Siamese Neural Networks (SNNs). A set of centroids from the patterns in the training data sets is calculated with supervised k-means clustering. The centroids are used to generate the dissimilarity space via the Siamese networks. The vector space descriptors are extracted by projecting patterns onto the similarity spaces, and SVMs classify an image by its dissimilarity vector. The versatility of the proposed approach in image classification is demonstrated by evaluating the system on different types of images across two domains: two medical data sets and two animal audio data sets with vocalizations represented as images (spectrograms). Results show that the proposed system's performance competes competitively against the best-performing methods in the literature, obtaining state-of-the-art performance on one of the medical data sets, and does so without ad-hoc optimization of the clustering methods on the tested data sets.

show abstract

Section: Introductionmentioning

confidence: 99%

Experiments of Image Classification Using Dissimilarity Spaces Built with Siamese Networks

Nanni

Minchio

Brahnam

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Though the two terms of similarity and dissimilarity are rarely disambiguated in the literature, classification based on the notion of dissimilarity is an idea first proposed in [ 1 ], where the focus was on comparing differences between samples belonging to different classes. Dissimilarity classification can be tackled by using either dissimilarity vectors, as in [ 2 , 3 , 4 , 5 , 6 ], or dissimilarity spaces, as in [ 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 ]. In the former case, two samples are considered positive if they belong to the same class and negative if they belong to separate classes.…”

Section: Introductionmentioning

confidence: 99%

“…This method was applied to image retrieval by [ 8 ] using a prototype-based dissimilarity space. In [ 10 ], a compact representation based on prototype selection methods was derived from deep convolutional features and learned distance measures.…”

Section: Introductionmentioning

confidence: 99%

Closing the Performance Gap between Siamese Networks for Dissimilarity Image Classification and Convolutional Neural Networks

Nanni

Minchio²,

Brahnam³

et al. 2021

Sensors

View full text Add to dashboard Cite

In this paper, we examine two strategies for boosting the performance of ensembles of Siamese networks (SNNs) for image classification using two loss functions (Triplet and Binary Cross Entropy) and two methods for building the dissimilarity spaces (FULLY and DEEPER). With FULLY, the distance between a pattern and a prototype is calculated by comparing two images using the fully connected layer of the Siamese network. With DEEPER, each pattern is described using a deeper layer combined with dimensionality reduction. The basic design of the SNNs takes advantage of supervised k-means clustering for building the dissimilarity spaces that train a set of support vector machines, which are then combined by sum rule for a final decision. The robustness and versatility of this approach are demonstrated on several cross-domain image data sets, including a portrait data set, two bioimage and two animal vocalization data sets. Results show that the strategies employed in this work to increase the performance of dissimilarity image classification using SNN are closing the gap with standalone CNNs. Moreover, when our best system is combined with an ensemble of CNNs, the resulting performance is superior to an ensemble of CNNs, demonstrating that our new strategy is extracting additional information.

show abstract

“…Though the two terms, similarity and dissimilarity are rarely disambiguated in the literature, classification based on the notion of dissimilarity is an idea first proposed in [1], where the focus was on comparing differences between samples belonging to different classes. Dissimilarity classification can be tackled by using either dissimilarity vectors, as in [2][3][4][5][6], or dissimilarity spaces, as in [7][8][9][10][11][12][13][14]. In the former case, two samples are considered positive if they belong to the same class and negative if they belong to separate classes.…”

Section: Introductionmentioning

confidence: 99%

Closing the Performance Gap between Siamese Networks for Dissimilarity Image Classification and Convolutional Neural Networks

Nanni¹,

Minchio²,

Brahnam³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we examine two strategies for boosting the performance of ensembles of Siamese networks (SNNs) for image classification using two loss functions (Triplet and Binary Cross Entropy) and two methods for building the dissimilarity spaces (FULLY and DEEPER). With FULLY, the distance between a pattern and a prototype is calculated by comparing two images using the fully connected layer of the Siamese network. With DEEPER, each pattern is described using a deeper layer combined with dimensionality reduction. The basic design of the SNNs takes advantage of supervised k-means clustering for building the dissimilarity spaces that train a set of support vector machines, which are then combined by sum rule for a final decision. The robustness and versatility of this approach are demonstrated on several cross-domain image data sets, including a portrait data set, two bioimage and two animal vocalization data sets. Results show that the strategies employed in this work to increase the performance of dissimilarity image classification using SNN is closing the gap with standalone CNNs. Moreover, when our best system is combined with an ensemble of CNNs, the resulting performance is superior to an ensemble of CNNs, demonstrating that our new strategy is extracting additional information.

show abstract

Low-Resolution Face Recognition with Deep Convolutional Features in the Dissimilarity Space

Cited by 6 publications

References 14 publications

Experiments of Image Classification Using Dissimilarity Spaces Built with Siamese Networks

Experiments of Image Classification Using Dissimilarity Spaces Built with Siamese Networks

Closing the Performance Gap between Siamese Networks for Dissimilarity Image Classification and Convolutional Neural Networks

Closing the Performance Gap between Siamese Networks for Dissimilarity Image Classification and Convolutional Neural Networks

Contact Info

Product

Resources

About