Face Verification via Class Sparsity Based Supervised Encoding
76
Citation
61
Reference
10
Related Paper
Citation Trend
Abstract:
Autoencoders are deep learning architectures that learn feature representation by minimizing the reconstruction error. Using an autoencoder as baseline, this paper presents a novel formulation for a class sparsity based supervised encoder, termed as CSSE. We postulate that features from the same class will have a common sparsity pattern/support in the latent space. Therefore, in the formulation of the autoencoder, a supervision penalty is introduced as a jointsparsity promoting l2;1-norm. The formulation of CSSE is derived for a single hidden layer and it is applied for multiple hidden layers using a greedy layer-bylayer learning approach. The proposed CSSE approach is applied for learning face representation and verification experiments are performed on the LFW and PaSC face databases. The experiments show that the proposed approach yields improved results compared to autoencoders and comparable results with state-ofthe-art face recognition algorithms.Keywords:
Autoencoder
Representation
Feature Learning
Feature (linguistics)
Autoencoder
Feature Learning
Feature (linguistics)
Representation
Cite
Citations (1)
Continuous audio recordings are playing an ever more important role in conservation and biodiversity monitoring, however, listening to these recordings is often infeasible, as they can be thousands of hours long. Automating analysis using machine learning is in high demand. However, these algorithms require a feature representation. Several methods for generating feature representations for these data have been developed, using techniques such as domain-specific features and deep learning. However, domain-specific features are unlikely to be an ideal representation of the data and deep learning methods often require extensively labeled data.In this paper, we propose a method for generating a frequency-preserving autoencoder-based feature representation for unlabeled ecological audio. We evaluate multiple frequency-preserving autoencoder-based feature representations using a hierarchical clustering sample task. We compare this to a basic autoencoder feature representation, MFCC, and spectral acoustic indices. Experimental results show that some of these non-square autoencoder architectures compare well to these existing feature representations.This novel method for generating a feature representation for unlabeled ecological audio will offer a fast, general way for ecologists to generate a feature representation of their audio, which does not require extensively labeled data.
Autoencoder
Feature Learning
Feature (linguistics)
Representation
Mel-frequency cepstrum
Spectrogram
Cite
Citations (0)
Continuous audio recordings are playing an ever more important role in conservation and biodiversity monitoring, however, listening to these recordings is often infeasible, as they can be thousands of hours long. Automating analysis using machine learning is in high demand. However, these algorithms require a feature representation. Several methods for generating feature representations for these data have been developed, using techniques such as domain-specific features and deep learning. However, domain-specific features are unlikely to be an ideal representation of the data and deep learning methods often require extensively labeled data.In this paper, we propose a method for generating a frequency-preserving autoencoder-based feature representation for unlabeled ecological audio. We evaluate multiple frequency-preserving autoencoder-based feature representations using a hierarchical clustering sample task. We compare this to a basic autoencoder feature representation, MFCC, and spectral acoustic indices. Experimental results show that some of these non-square autoencoder architectures compare well to these existing feature representations.This novel method for generating a feature representation for unlabeled ecological audio will offer a fast, general way for ecologists to generate a feature representation of their audio, which does not require extensively labeled data.
Autoencoder
Feature Learning
Feature (linguistics)
Representation
Mel-frequency cepstrum
Cite
Citations (2)
Cyclic codes are often used in encoders to avoid possible erroneous readings. Special attention must be paid to codes where changes in certain digits are ``irregular.'' An angular encoder that provides readings in degrees is such an example. A new cyclic encoding scheme for a degree-reading encoder is proposed in this paper. While keeping the encoding simple and efficient, the method considerably reduces the external decoding circuit requirements.
Cite
Citations (0)
Standard basic encoding rules are too elaborate and inefficient for distributed real-time applications. Two major obstacles encountered are long protocol data units and slow encoding times. The problem of encoding for real-time applications is addressed. Taking Fieldbus as a representative of real-time networks, it is shown why the encoder should be simplified and how this can be done. The impact of encoders, in general, on the overall network performance is studied. Implementation results demonstrate the efficiency of the proposed encoder.< >
Cite
Citations (1)
Autoencoder
Feature Learning
Feature (linguistics)
Representation
Cite
Citations (1)
Autoencoder
Discriminative model
Feature Learning
Representation
Feature (linguistics)
Domain Adaptation
Cite
Citations (13)
The last decades have witnessed a vast amount of interest and research in feature representation learning from multiple disciplines, such as biology and bioinformatics. Among all the real-world application scenarios, feature extraction from knowledge graph (KG) for personalized recommendation has achieved substantial performance for addressing the problem of information overload. However, the rating matrix of recommendations is usually sparse, which may result in significant performance degradation. The crucial problem is how to extract and extend features from additional side information. To address these issues, we propose a novel feature representation learning method for the recommendation in this paper that extends item features with knowledge graph via triple-autoencoder. More specifically, the comment information between users and items is first encoded as sentiment classification. These features are then applied as the input to the autoencoder for generating the auxiliary information of items. Second, the item-based rating, the side information, and the generated comment representations are incorporated into the semi-autoencoder for reconstructed output. The low-dimensional representations of this extended information are learned with the semi-autoencoder. Finally, the reconstructed output generated by the semi-autoencoder is input into a third autoencoder. A serial connection between the semi-autoencoder and the autoencoder is designed here to learn more abstract and higher-level feature representations for personalized recommendation. Extensive experiments conducted on several real-world datasets validate the effectiveness of the proposed method compared to several state-of-the-art models.
Autoencoder
Feature Learning
Information Overload
Representation
Feature (linguistics)
Cite
Citations (5)
Modern codecs offer numerous settings that can alter the encoding process. Multiobjective video encoding optimization has been studied in various works, but the whole encoder's option space was never considered. In this paper, we present a method for multiobjective encoding optimization in terms of relative video bitrate and encoding speed over the entire option space for a given encoder.
Cite
Citations (1)
We have developed a small, low-power HDTV MPEG-2 encoder based on a spatially parallel encoding approach. The encoder consists of multiple enhanced SDTV encoding LSIs, which have already been used to develop a single-chip, low-power MP@ML MPEG-2 video encoder.
MPEG-2
MPEG-4
Cite
Citations (8)