Human perceives rich auditory experience with distinct sound heard by ears. Videos recorded with binaural audio particular simulate how human receives ambient sound. However, a large number of videos are with monaural audio only, which would degrade the user experience due to the lack of ambient information. To address this issue, we propose an audio spatialization framework to convert a monaural video into a binaural one exploiting the relationship across audio and visual components. By preserving the left-right consistency in both audio and visual modalities, our learning strategy can be viewed as a self-supervised learning technique, and alleviates the dependency on a large amount of video data with ground truth binaural audio data during training. Experiments on benchmark datasets confirm the effectiveness of our proposed framework in both semi-supervised and fully supervised scenarios, with ablation studies and visualization further support the use of our model for audio spatialization.
Transparency is a key factor in improving the performance of human-robot interaction. A transparent interface allows humans to be aware of the state of a robot and to assess the progress of the tasks at hand. When multi-robot systems are involved, transparency is an even greater challenge, due to the larger number of variables affecting the behavior of the robots as a whole. Significant effort has been devoted to studying transparency when single operators interact with multiple robots. However, studies on transparency that focus on multiple human operators interacting with a multi-robot systems are limited. This paper aims to fill this gap by presenting a human-swarm interaction interface with graphical elements that can be enabled and disabled. Through this interface, we study which graphical elements are contribute to transparency by comparing four "transparency modes": (i) no transparency (no operator receives information from the robots), (ii) central transparency (the operators receive information only relevant to their personal task), (iii) peripheral transparency (the operators share information on each others' tasks), and (iv) mixed transparency (both central and peripheral). We report the results in terms of awareness, trust, and workload of a user study involving 18 participants engaged in a complex multi-robot task.
This paper presents a new proposal of an efficient computational model of face and object recognition which uses cues from the distributed face and object recognition mechanism of the brain, and by gathering engineering equivalent of these cues from existing literature. Three distinct and widely used features, Histogram of Oriented Gradients, Local Binary Patterns, and Principal components extracted from target images are used in a manner which is simple, and yet effective. Our model uses multi-layer perceptrons (MLP) to classify these three features and fuse them at the decision level using sum rule. A computational theory is first developed by using concepts from the information processing mechanism of the brain. Extensive experiments are carried out using fifteen publicly available datasets to validate the performance of our proposed model in recognizing faces and objects with extreme variation of illumination, pose angle, expression, and background. Results obtained are extremely promising when compared with other face and object recognition algorithms including CNN and deep learning based methods. This highlights that simple computational processes, if clubbed properly, can produce competing performance with best algorithms.
The cross-entropy loss commonly used in deep learning is closely related to the defining properties of optimal representations, but does not enforce some of the key properties. We show that this can be solved by adding a regularization term, which is in turn related to injecting multiplicative noise in the activations of a Deep Neural Network, a special case of which is the common practice of dropout. We show that our regularized loss function can be efficiently minimized using Information Dropout, a generalization of dropout rooted in information theoretic principles that automatically adapts to the data and can better exploit architectures of limited capacity. When the task is the reconstruction of the input, we show that our loss function yields a Variational Autoencoder as a special case, thus providing a link between representation learning, information theory and variational inference. Finally, we prove that we can promote the creation of disentangled representations simply by enforcing a factorized prior, a fact that has been observed empirically in recent work. Our experiments validate the theoretical intuitions behind our method, and we find that information dropout achieves a comparable or better generalization performance than binary dropout, especially on smaller models, since it can automatically adapt the noise to the structure of the network, as well as to the test sample.
In retrieval applications, binary hashes are known to offer significant improvements in terms of both memory and speed. We investigate the compression of sentence embeddings using a neural encoder-decoder architecture, which is trained by minimizing reconstruction error. Instead of employing the original real-valued embeddings, we use latent representations in Hamming space produced by the encoder for similarity calculations. In quantitative experiments on several benchmarks for semantic similarity tasks, we show that our compressed hamming embeddings yield a comparable performance to uncompressed embeddings (Sent2Vec, InferSent, Glove-BoW), at compression ratios of up to 256:1. We further demonstrate that our model strongly decorrelates input features, and that the compressor generalizes well when pre-trained on Wikipedia sentences. We publish the source code on Github and all experimental results.
Stein variational gradient descent (SVGD) refers to a class of methods for Bayesian inference based on interacting particle systems. In this paper, we consider the originally proposed deterministic dynamics as well as a stochastic variant, each of which represent one of the two main paradigms in Bayesian computational statistics: variational inference and Markov chain Monte Carlo. As it turns out, these are tightly linked through a correspondence between gradient flow structures and large-deviation principles rooted in statistical physics. To expose this relationship, we develop the cotangent space construction for the Stein geometry, prove its basic properties, and determine the large-deviation functional governing the many-particle limit for the empirical measure. Moreover, we identify the Stein-Fisher information (or kernelised Stein discrepancy) as its leading order contribution in the long-time and many-particle regime in the sense of $\Gamma$-convergence, shedding some light on the finite-particle properties of SVGD. Finally, we establish a comparison principle between the Stein-Fisher information and RKHS-norms that might be of independent interest.
There is currently a gap between the natural language expression of scholarly publications and their structured semantic content modeling to enable intelligent content search. With the volume of research growing exponentially every year, a search feature operating over semantically structured content is compelling. The SemEval-2021 Shared Task NLPContributionGraph (a.k.a. 'the NCG task') tasks participants to develop automated systems that structure contributions from NLP scholarly articles in the English language. Being the first-of-its-kind in the SemEval series, the task released structured data from NLP scholarly articles at three levels of information granularity, i.e. at sentence-level, phrase-level, and phrases organized as triples toward Knowledge Graph (KG) building. The sentence-level annotations comprised the few sentences about the article's contribution. The phrase-level annotations were scientific term and predicate phrases from the contribution sentences. Finally, the triples constituted the research overview KG. For the Shared Task, participating systems were then expected to automatically classify contribution sentences, extract scientific terms and relations from the sentences, and organize them as KG triples. Overall, the task drew a strong participation demographic of seven teams and 27 participants. The best end-to-end task system classified contribution sentences at 57.27% F1, phrases at 46.41% F1, and triples at 22.28% F1. While the absolute performance to generate triples remains low, in the conclusion of this article, the difficulty of producing such data and as a consequence of modeling it is highlighted.
In open domain table-to-text generation, we notice that the unfaithful generation usually contains hallucinated content which can not be aligned to any input table record. We thus try to evaluate the generation faithfulness with two entity-centric metrics: table record coverage and the ratio of hallucinated entities in text, both of which are shown to have strong agreement with human judgements. Then based on these metrics, we quantitatively analyze the correlation between training data quality and generation fidelity which indicates the potential usage of entity information in faithful generation. Motivated by these findings, we propose two methods for faithful generation: 1) augmented training by incorporating the auxiliary entity information, including both an augmented plan-based model and an unsupervised model and 2) training instance selection based on faithfulness ranking. We show these approaches improve generation fidelity in both full dataset setting and few shot learning settings by both automatic and human evaluations.
Recently, knowledge distillation (KD) has shown great success in BERT compression. Instead of only learning from the teacher's soft label as in conventional KD, researchers find that the rich information contained in the hidden layers of BERT is conducive to the student's performance. To better exploit the hidden knowledge, a common practice is to force the student to deeply mimic the teacher's hidden states of all the tokens in a layer-wise manner. In this paper, however, we observe that although distilling the teacher's hidden state knowledge (HSK) is helpful, the performance gain (marginal utility) diminishes quickly as more HSK is distilled. To understand this effect, we conduct a series of analysis. Specifically, we divide the HSK of BERT into three dimensions, namely depth, length and width. We first investigate a variety of strategies to extract crucial knowledge for each single dimension and then jointly compress the three dimensions. In this way, we show that 1) the student's performance can be improved by extracting and distilling the crucial HSK, and 2) using a tiny fraction of HSK can achieve the same performance as extensive HSK distillation. Based on the second finding, we further propose an efficient KD paradigm to compress BERT, which does not require loading the teacher during the training of student. For two kinds of student models and computing devices, the proposed KD paradigm gives rise to training speedup of 2.7x ~ 3.4x.
Adversarial algorithms have shown to be effective against neural networks for a variety of tasks. Some adversarial algorithms perturb all the pixels in the image minimally for the image classification task in image classification. In contrast, some algorithms perturb few pixels strongly. However, very little information is available regarding why these adversarial samples so diverse from each other exist. Recently, Vargas et al. showed that the existence of these adversarial samples might be due to conflicting saliency within the neural network. We test this hypothesis of conflicting saliency by analysing the Saliency Maps (SM) and Gradient-weighted Class Activation Maps (Grad-CAM) of original and few different types of adversarial samples. We also analyse how different adversarial samples distort the attention of the neural network compared to original samples. We show that in the case of Pixel Attack, perturbed pixels either calls the network attention to themselves or divert the attention from them. Simultaneously, the Projected Gradient Descent Attack perturbs pixels so that intermediate layers inside the neural network lose attention for the correct class. We also show that both attacks affect the saliency map and activation maps differently. Thus, shedding light on why some defences successful against some attacks remain vulnerable against other attacks. We hope that this analysis will improve understanding of the existence and the effect of adversarial samples and enable the community to develop more robust neural networks.