We consider quantitative analyses of spectral data using laser-induced breakdown spectroscopy. We address the small size of training data available, and the validation of the predictions during inference on unknown data. For the purpose, we build robust calibration models using deep convolutional multitask learning architectures to predict the concentration of the analyte, alongside additional spectral information as auxiliary outputs. These secondary predictions can be used to validate the trustworthiness of the model by taking advantage of the mutual dependencies of the parameters of the multitask neural networks. Due to the experimental lack of training samples, we introduce a simulation-based data augmentation process to synthesise an arbitrary number of spectra, statistically representative of the experimental data. Given the nature of the deep learning model, no dimensionality reduction or data selection processes are required. The procedure is an end-to-end pipeline including the process of synthetic data augmentation, the construction of a suitable robust, homoscedastic, deep learning model, and the validation of its predictions. In the article, we compare the performance of the multitask model with traditional univariate and multivariate analyses, to highlight the separate contributions of each element introduced in the process.
We leverage the modern advancements in talking head generation to propose an end-to-end system for talking head video compression. Our algorithm transmits pivot frames intermittently while the rest of the talking head video is generated by animating them. We use a state-of-the-art face reenactment network to detect key points in the non-pivot frames and transmit them to the receiver. A dense flow is then calculated to warp a pivot frame to reconstruct the non-pivot ones. Transmitting key points instead of full frames leads to significant compression. We propose a novel algorithm to adaptively select the best-suited pivot frames at regular intervals to provide a smooth experience. We also propose a frame-interpolater at the receiver's end to improve the compression levels further. Finally, a face enhancement network improves reconstruction quality, significantly improving several aspects like the sharpness of the generations. We evaluate our method both qualitatively and quantitatively on benchmark datasets and compare it with multiple compression techniques. We release a demo video and additional information at https://cvit.iiit.ac.in/research/projects/cvit-projects/talking-video-compression.
We present a neural point cloud rendering pipeline through a novel multi-frequency-aware patch adversarial learning framework. The proposed approach aims to improve the rendering realness by minimizing the spectrum discrepancy between real and synthesized images, especially on the high-frequency localized sharpness information which causes image blur visually. Specifically, a patch multi-discriminator scheme is proposed for the adversarial learning, which combines both spectral domain (Fourier Transform and Discrete Wavelet Transform) discriminators as well as the spatial (RGB) domain discriminator to force the generator to capture global and local spectral distributions of the real images. The proposed multi-discriminator scheme not only helps to improve rendering realness, but also enhance the convergence speed and stability of adversarial learning. Moreover, we introduce a noise-resistant voxelisation approach by utilizing both the appearance distance and spatial distance to exclude the spatial outlier points caused by depth noise. Our entire architecture is fully differentiable and can be learned in an end-to-end fashion. Extensive experiments show that our method produces state-of-the-art results for neural point cloud rendering by a significant margin. Our source code will be made public at a later date.
In unsupervised person Re-ID, peer-teaching strategy leveraging two networks to facilitate training has been proven to be an effective method to deal with the pseudo label noise. However, training two networks with a set of noisy pseudo labels reduces the complementarity of the two networks and results in label noise accumulation. To handle this issue, this paper proposes a novel Dual Clustering Co-teaching (DCCT) approach. DCCT mainly exploits the features extracted by two networks to generate two sets of pseudo labels separately by clustering with different parameters. Each network is trained with the pseudo labels generated by its peer network, which can increase the complementarity of the two networks to reduce the impact of noises. Furthermore, we propose dual clustering with dynamic parameters (DCDP) to make the network adaptive and robust to dynamically changing clustering parameters. Moreover, Consistent Sample Mining (CSM) is proposed to find the samples with unchanged pseudo labels during training for potential noisy sample removal. Extensive experiments demonstrate the effectiveness of the proposed method, which outperforms the state-of-the-art unsupervised person Re-ID methods by a considerable margin and surpasses most methods utilizing camera information.
This letter studies the ergodic mutual information (EMI) of keyhole multiple-input multiple-output (MIMO) channels having finite input signals. At first, the EMI of single-stream transmission is investigated depending on whether the channel state information at the transmitter (CSIT) is available or not. Then, the derived results are extended to the case of multi-stream transmission. For the sake of providing more system insights, asymptotic analyses are performed in the regime of high signal-to-noise ratio (SNR), which suggests that the high-SNR EMI converges to some constant with its rate of convergence (ROC) determined by the diversity order. All the results are validated by numerical simulations and are in excellent agreement.
In limited feedback multi-user multiple-input multiple-output (MU-MIMO) cellular networks, users send quantized information about the channel conditions to the associated base station (BS) for downlink beamforming. However, channel quantization and beamforming have been treated as two separate tasks conventionally, which makes it difficult to achieve global system optimality. In this paper, we propose an augmented deep unfolding (ADU) approach that jointly optimizes the beamforming scheme at the BSs and the channel quantization scheme at the users. In particular, the classic WMMSE beamformer is unrolled and a deep neural network (DNN) is leveraged to pre-process its input to enhance the performance. The variational information bottleneck technique is adopted to further improve the performance when the feedback capacity is strictly restricted. Simulation results demonstrate that the proposed ADU method outperforms all the benchmark schemes in terms of the system average rate.
We introduce an information criterion, PCIC, for predictive evaluation based on quasi-posterior distributions. It is regarded as a natural generalization of widely applicable information criterion (WAIC) and can be computed via a single Markov Chain Monte Carlo run. PCIC is useful in a variety of predictive settings that are not well dealt with in WAIC, including weighted likelihood inference and quasi-Bayesian prediction.
This paper proposes the MBURST, a novel multimodal solution for audio-visual speech enhancements that consider the most recent neurological discoveries regarding pyramidal cells of the prefrontal cortex and other brain regions. The so-called burst propagation implements several criteria to address the credit assignment problem in a more biologically plausible manner: steering the sign and magnitude of plasticity through feedback, multiplexing the feedback and feedforward information across layers through different weight connections, approximating feedback and feedforward connections, and linearizing the feedback signals. MBURST benefits from such capabilities to learn correlations between the noisy signal and the visual stimuli, thus attributing meaning to the speech by amplifying relevant information and suppressing noise. Experiments conducted over a Grid Corpus and CHiME3-based dataset show that MBURST can reproduce similar mask reconstructions to the multimodal backpropagation-based baseline while demonstrating outstanding energy efficiency management, reducing the neuron firing rates to values up to \textbf{$70\%$} lower. Such a feature implies more sustainable implementations, suitable and desirable for hearing aids or any other similar embedded systems.
Self-supervised representations have been extensively studied for discriminative and generative tasks. However, their robustness capabilities have not been extensively investigated. This work focuses on self-supervised representations for spoken generative language models. First, we empirically demonstrate how current state-of-the-art speech representation models lack robustness to basic signal variations that do not alter the spoken information. To overcome this, we propose an effective and efficient method to learn robust self-supervised speech representation for generative spoken language modeling. The proposed approach is based on applying a set of signal transformations to the speech signal and optimizing the model using an iterative pseudo-labeling scheme. Our method significantly improves over the evaluated baselines when considering encoding metrics. We additionally evaluate our method on the speech-to-speech translation task. We consider Spanish-English and French-English conversions and empirically demonstrate the benefits of following the proposed approach.
The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). However, self-attention and multi-head attention cannot be easily applied for streaming or online ASR. For self-attention in Transformer ASR, the softmax normalization function-based attention mechanism makes it impossible to highlight important speech information. For multi-head attention in Transformer ASR, it is not easy to model monotonic alignments in different heads. To overcome these two limits, we integrate sparse attention and monotonic attention into Transformer-based ASR. The sparse mechanism introduces a learned sparsity scheme to enable each self-attention structure to fit the corresponding head better. The monotonic attention deploys regularization to prune redundant heads for the multi-head attention structure. The experiments show that our method can effectively improve the attention mechanism on widely used benchmarks of speech recognition.