- Read more about One-class Learning Towards Synthetic Voice Spoofing Detection (Poster)
- Log in to post comments

Human voices can be used to authenticate the identity of the speaker, but the automatic speaker verification (ASV) systems are vulnerable to voice spoofing attacks, such as impersonation, replay, text-to-speech, and voice conversion. Recently, researchers developed anti-spoofing techniques to improve the reliability of ASV systems against spoofing attacks. However, most methods encounter difficulties in detecting unknown attacks in practical use, which often have different statistical distributions from known attacks.

- Categories:

- Read more about Information Preserving Dimensionality Reduction for Mutual Information Analysis of Deep Learning
- Log in to post comments

Mutual information has been actively investigated as a tool for analyzing neural networks' behavior, most notably the information bottleneck theory. However, estimating mutual information is a notoriously tricky task, especially for high-dimensional stochastic variables. Recently, mutual information neural estimation (MINE) was proposed as a non-parametric method to estimate mutual information for continuous variables without discretization. Unfortunately, MINE also produces significant errors for high-dimensional variables.

- Categories:

- Read more about Graph-based Transform based on 3D Convolutional Neural Network for Intra-Prediction of Imaging Data
- Log in to post comments

This paper presents a novel class of Graph-based Transform based on 3D convolutional neural networks (GBT-CNN) within the context of block-based predictive transform coding of imaging data. The proposed GBT-CNN uses a 3D convolutional neural network (3D-CNN) to predict the graph information needed to compute the transform and its inverse, thus reducing the signalling cost to reconstruct the data after transformation.

- Categories:

- Read more about Neural Distributed Image Compression Using Common Information
- Log in to post comments

We present a novel deep neural network (DNN) architecture for compressing an image when a correlated image is available as side information only at the decoder. This problem is known as distributed source coding (DSC) in information theory. In particular, we consider a pair of stereo images, which generally have high correlation with each other due to overlapping fields of view, and assume that one image of the pair is to be compressed and transmitted, while the other image is available only at the decoder.

- Categories:

- Read more about Deep Correlated Image Set Compression Based on Distributed Source Coding and Multi-Scale Fusion
- Log in to post comments

In this paper, we present a deep correlated image set compression scheme based on Distributed Source Coding(DSC) and multi-scale image fusion. As there exists strong correlation among images in a similar image set, we propose to utilize such correlation to generate side information at decoder side for each image in the set. Specifically, a reference structure of the image set is generated by building a minimum spanning tree according to the similarity between two images at encoder.

- Categories:

- Read more about Neural JPEG: End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder
- Log in to post comments

Recent advances in deep learning have led to superhuman performance across a variety of applications. Recently, these methods have been successfully employed to improve the rate-distortion performance in the task of image compression.

- Categories:

- Categories:

- Read more about Analysis on Compressed Domain: A Multi-Task Learning Approach
- 2 comments
- Log in to post comments

Image compression approaches based on deep learning have achieved remarkable success.

Existing studies mainly focus on human vision and machine analysis tasks taking reconstructed images as input.

- Categories:

- Read more about Less is More: Compression of Deep Neural Networks for adaptation in photonic FPGA circuits
- Log in to post comments

Photonic circuits pave the way to ultrafast computing and real-time inference of applications with paramount importance, such as imaging flow cytometry (IFC). However, current implementations exhibit inherent restrictions that consequently diminish the neural networks (NN) complexity that can be supported. Thus, NN compression mechanisms are deemed critical for the efficient deployment of such demanding tasks.

- Categories:

- Read more about Interpretable Learned Image Compression: A Frequency Transform Decomposition Perspective
- 1 comment
- Log in to post comments

Image compression is a key problem in this age of information explosion. With the help of machine learning, recent studies have shown that learning-based image compression methods tend to surpass traditional codecs. Image compression can be split into three steps: transform, quantization, and entropy estimation.

- Categories: