Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization

Nov 12, 2021
Byeonggeun Kim, Seunghan Yang, Jangho Kim, Simyung Chang

It is a practical research topic how to deal with multi-device audio inputs by a single acoustic scene classification system with efficient design. In this work, we propose Residual Normalization, a novel feature normalization method that uses frequency-wise normalization % instance normalization with a shortcut path to discard unnecessary device-specific information without losing useful information for classification. Moreover, we introduce an efficient architecture, BC-ResNet-ASC, a modified version of the baseline architecture with a limited receptive field. BC-ResNet-ASC outperforms the baseline architecture even though it contains the small number of parameters. Through three model compression schemes: pruning, quantization, and knowledge distillation, we can reduce model complexity further while mitigating the performance degradation. The proposed system achieves an average test accuracy of 76.3% in TAU Urban Acoustic Scenes 2020 Mobile, development dataset with 315k parameters, and average test accuracy of 75.3% after compression to 61.0KB of non-zero parameters. The proposed method won the 1st place in DCASE 2021 challenge, TASK1A.

* Proceedings of the Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021) 

  Access Paper or Ask Questions

A causal view on compositional data

Jun 21, 2021
Elisabeth Ailer, Christian L. Müller, Niki Kilbertus

Many scientific datasets are compositional in nature. Important examples include species abundances in ecology, rock compositions in geology, topic compositions in large-scale text corpora, and sequencing count data in molecular biology. Here, we provide a causal view on compositional data in an instrumental variable setting where the composition acts as the cause. Throughout, we pay particular attention to the interpretation of compositional causes from the viewpoint of interventions and crisply articulate potential pitfalls for practitioners. Focusing on modern high-dimensional microbiome sequencing data as a timely illustrative use case, our analysis first reveals that popular one-dimensional information-theoretic summary statistics, such as diversity and richness, may be insufficient for drawing causal conclusions from ecological data. Instead, we advocate for multivariate alternatives using statistical data transformations and regression techniques that take the special structure of the compositional sample space into account. In a comparative analysis on synthetic and semi-synthetic data we show the advantages and limitations of our proposal. We posit that our framework may provide a useful starting point for cause-effect estimation in the context of compositional data.

* Code available on 

  Access Paper or Ask Questions

Sound-to-Imagination: Unsupervised Crossmodal Translation Using Deep Dense Network Architecture

Jun 02, 2021
Leonardo A. Fanzeres, Climent Nadeu

The motivation of our research is to develop a sound-to-image (S2I) translation system for enabling a human receiver to visually infer the occurrence of sound related events. We expect the computer to 'imagine' the scene from the captured sound, generating original images that picture the sound emitting source. Previous studies on similar topics opted for simplified approaches using data with low content diversity and/or strong supervision. Differently, we propose to perform unsupervised S2I translation using thousands of distinct and unknown scenes, with slightly pre-cleaned data, just enough to guarantee aural-visual semantic coherence. To that end, we employ conditional generative adversarial networks (GANs) with a deep densely connected generator. Besides, we implemented a moving-average adversarial loss to address GANs training instability. Though the specified S2I translation problem is quite challenging, we were able to generalize the translator model enough to obtain more than 14%, in average, of interpretable and semantically coherent images translated from unknown sounds. Additionally, we present a solution using informativity classifiers to perform quantitative evaluation of S2I translation.

  Access Paper or Ask Questions

Improved Exploring Starts by Kernel Density Estimation-Based State-Space Coverage Acceleration in Reinforcement Learning

May 19, 2021
Maximilian Schenke, Oliver Wallscheid

Reinforcement learning (RL) is currently a popular research topic in control engineering and has the potential to make its way to industrial and commercial applications. Corresponding RL controllers are trained in direct interaction with the controlled system, rendering them data-driven and performance-oriented solutions. The best practice of exploring starts (ES) is used by default to support the learning process via randomly picked initial states. However, this method might deliver strongly biased results if the system's dynamic and constraints lead to unfavorable sample distributions in the state space (e.g., condensed sample accumulation in certain state-space areas). To overcome this issue, a kernel density estimation-based state-space coverage acceleration (DESSCA) is proposed, which improves the ES concept by prioritizing infrequently visited states for a more balanced coverage of the state space during training. Considered test scenarios are mountain car, cartpole and electric motor control environments. Using DQN and DDPG as exemplary RL algorithms, it can be shown that DESSCA is a simple yet effective algorithmic extension to the established ES approach.

  Access Paper or Ask Questions

Person Search Challenges and Solutions: A Survey

May 01, 2021
Xiangtan Lin, Pengzhen Ren, Yun Xiao, Xiaojun Chang, Alex Hauptmann

Person search has drawn increasing attention due to its real-world applications and research significance. Person search aims to find a probe person in a gallery of scene images with a wide range of applications, such as criminals search, multicamera tracking, missing person search, etc. Early person search works focused on image-based person search, which uses person image as the search query. Text-based person search is another major person search category that uses free-form natural language as the search query. Person search is challenging, and corresponding solutions are diverse and complex. Therefore, systematic surveys on this topic are essential. This paper surveyed the recent works on image-based and text-based person search from the perspective of challenges and solutions. Specifically, we provide a brief analysis of highly influential person search methods considering the three significant challenges: the discriminative person features, the query-person gap, and the detection-identification inconsistency. We summarise and compare evaluation results. Finally, we discuss open issues and some promising future research directions.

* 8 pages; Accepted by IJCAI 2021 Survey Track 

  Access Paper or Ask Questions

SRA-LSTM: Social Relationship Attention LSTM for Human Trajectory Prediction

Mar 31, 2021
Yusheng Peng, Gaofeng Zhang, Jun Shi, Benzhu Xu, Liping Zheng

Pedestrian trajectory prediction for surveillance video is one of the important research topics in the field of computer vision and a key technology of intelligent surveillance systems. Social relationship among pedestrians is a key factor influencing pedestrian walking patterns but was mostly ignored in the literature. Pedestrians with different social relationships play different roles in the motion decision of target pedestrian. Motivated by this idea, we propose a Social Relationship Attention LSTM (SRA-LSTM) model to predict future trajectories. We design a social relationship encoder to obtain the representation of their social relationship through the relative position between each pair of pedestrians. Afterwards, the social relationship feature and latent movements are adopted to acquire the social relationship attention of this pair of pedestrians. Social interaction modeling is achieved by utilizing social relationship attention to aggregate movement information from neighbor pedestrians. Experimental results on two public walking pedestrian video datasets (ETH and UCY), our model achieves superior performance compared with state-of-the-art methods. Contrast experiments with other attention methods also demonstrate the effectiveness of social relationship attention.

* Submitted to Neural Computing and Applications 

  Access Paper or Ask Questions

IC Networks: Remodeling the Basic Unit for Convolutional Neural Networks

Feb 06, 2021
Junyi An, Fengshan Liu, Jian Zhao, Furao Shen

Convolutional neural network (CNN) is a class of artificial neural networks widely used in computer vision tasks. Most CNNs achieve excellent performance by stacking certain types of basic units. In addition to increasing the depth and width of the network, designing more effective basic units has become an important research topic. Inspired by the elastic collision model in physics, we present a general structure which can be integrated into the existing CNNs to improve their performance. We term it the "Inter-layer Collision" (IC) structure. Compared to the traditional convolution structure, the IC structure introduces nonlinearity and feature recalibration in the linear convolution operation, which can capture more fine-grained features. In addition, a new training method, namely weak logit distillation (WLD), is proposed to speed up the training of IC networks by extracting knowledge from pre-trained basic models. In the ImageNet experiment, we integrate the IC structure into ResNet-50 and reduce the top-1 error from 22.38% to 21.75%, which also catches up the top-1 error of ResNet-100 (21.75%) with nearly half of FLOPs.

* 7 pages, 3 figure 

  Access Paper or Ask Questions

Signal Processing on Higher-Order Networks: Livin' on the Edge ... and Beyond

Jan 14, 2021
Michael T. Schaub, Yu Zhu, Jean-Baptiste Seby, T. Mitchell Roddenberry, Santiago Segarra

This tutorial paper presents a didactic treatment of the emerging topic of signal processing on higher-order networks. Drawing analogies from discrete and graph signal processing, we introduce the building blocks for processing data on simplicial complexes and hypergraphs, two common abstractions of higher-order networks that can incorporate polyadic relationships.We provide basic introductions to simplicial complexes and hypergraphs, making special emphasis on the concepts needed for processing signals on them. Leveraging these concepts, we discuss Fourier analysis, signal denoising, signal interpolation, node embeddings, and non-linear processing through neural networks in these two representations of polyadic relational structures. In the context of simplicial complexes, we specifically focus on signal processing using the Hodge Laplacian matrix, a multi-relational operator that leverages the special structure of simplicial complexes and generalizes desirable properties of the Laplacian matrix in graph signal processing. For hypergraphs, we present both matrix and tensor representations, and discuss the trade-offs in adopting one or the other. We also highlight limitations and potential research avenues, both to inform practitioners and to motivate the contribution of new researchers to the area.

* 38 pages; 7 figures 

  Access Paper or Ask Questions

Exploring and Analyzing Machine Commonsense Benchmarks

Dec 21, 2020
Henrique Santos, Minor Gordon, Zhicheng Liang, Gretchen Forbush, Deborah L. McGuinness

Commonsense question-answering (QA) tasks, in the form of benchmarks, are constantly being introduced for challenging and comparing commonsense QA systems. The benchmarks provide question sets that systems' developers can use to train and test new models before submitting their implementations to official leaderboards. Although these tasks are created to evaluate systems in identified dimensions (e.g. topic, reasoning type), this metadata is limited and largely presented in an unstructured format or completely not present. Because machine common sense is a fast-paced field, the problem of fully assessing current benchmarks and systems with regards to these evaluation dimensions is aggravated. We argue that the lack of a common vocabulary for aligning these approaches' metadata limits researchers in their efforts to understand systems' deficiencies and in making effective choices for future tasks. In this paper, we first discuss this MCS ecosystem in terms of its elements and their metadata. Then, we present how we are supporting the assessment of approaches by initially focusing on commonsense benchmarks. We describe our initial MCS Benchmark Ontology, an extensible common vocabulary that formalizes benchmark metadata, and showcase how it is supporting the development of a Benchmark tool that enables benchmark exploration and analysis.

* Commonsense Knowledge Graphs Workshop 2021 (CSKGs) @AAAI-21 

  Access Paper or Ask Questions

Approximation of BV functions by neural networks: A regularity theory approach

Dec 15, 2020
Benny Avelin, Vesa Julin

In this paper we are concerned with the approximation of functions by single hidden layer neural networks with ReLU activation functions on the unit circle. In particular, we are interested in the case when the number of data-points exceeds the number of nodes. We first study the convergence to equilibrium of the stochastic gradient flow associated with the cost function with a quadratic penalization. Specifically, we prove a Poincar\'e inequality for a penalized version of the cost function with explicit constants that are independent of the data and of the number of nodes. As our penalization biases the weights to be bounded, this leads us to study how well a network with bounded weights can approximate a given function of bounded variation (BV). Our main contribution concerning approximation of BV functions, is a result which we call the localization theorem. Specifically, it states that the expected error of the constrained problem, where the length of the weights are less than $R$, is of order $R^{-1/9}$ with respect to the unconstrained problem (the global optimum). The proof is novel in this topic and is inspired by techniques from regularity theory of elliptic partial differential equations. Finally we quantify the expected value of the global optimum by proving a quantitative version of the universal approximation theorem.

  Access Paper or Ask Questions