In this paper, we propose a method for incremental learning of two distinct tasks over time: acoustic scene classification (ASC) and audio tagging (AT). We use a simple convolutional neural network (CNN) model as an incremental learner to solve the tasks. Generally, incremental learning methods catastrophically forget the previous task when sequentially trained on a new task. To alleviate this problem, we propose independent learning and knowledge distillation (KD) between the timesteps in learning. Experiments are performed on TUT 2016/2017 dataset, containing 4 acoustic scene classes and 25 sound event classes. The proposed incremental learner first solves the ASC task with an accuracy of 94.0%. Next, it learns to solve the AT task with an F1 score of 54.4%. At the same time, its performance on the previous ASC task decreases only by 5.1 percentage points due to the additional learning of the AT task.
相關內容
In this paper, with the goal of quantifying the qualitative image outputs of a Vision-based Tactile Sensor (VTS), we present the design, fabrication, and characterization of a novel Quantitative Surface Tactile Sensor (called QS-TS). QS-TS directly estimates the sensor's gel layer deformation in real-time enabling safe and autonomous tactile manipulation and servoing of delicate objects using robotic manipulators. The core of the proposed sensor is the utilization of miniature 1.5 mm x 1.5 mm synthetic square markers with inner binary patterns and a broad black border, called ArUco Markers. Each ArUco marker can provide real-time camera pose estimation that, in our design, is used as a quantitative measure for obtaining deformation of the QS-TS gel layer. Moreover, thanks to the use of ArUco markers, we propose a unique fabrication procedure that mitigates various challenges associated with the fabrication of the existing marker-based VTSs and offers an intuitive and less-arduous method for the construction of the VTS. Remarkably, the proposed fabrication facilitates the integration and adherence of markers with the gel layer to robustly and reliably obtain a quantitative measure of deformation in real-time regardless of the orientation of ArUco Markers. The performance and efficacy of the proposed QS-TS in estimating the deformation of the sensor's gel layer were experimentally evaluated and verified. Results demonstrate the phenomenal performance of the QS-TS in estimating the deformation of the gel layer with a relative error of <5%.
This paper makes two theoretical contributions. First, we establish a novel class of Hamiltonian systems, called arc Hamiltonian systems, for saddle Hamiltonian functions over infinite-dimensional metric spaces. Arc Hamiltonian systems generate a flow that satisfies the law of conservation of energy everywhere in a metric space. They are governed by an extension of Hamilton's equation formulated based on (i) the framework of arc fields and (ii) an infinite-dimensional gradient, termed the arc gradient, of a Hamiltonian function. We derive conditions for the existence of a flow generated by an arc Hamiltonian system, showing that they reduce to local Lipschitz continuity of the arc gradient under sufficient regularity. Second, we present two Hamiltonian functions, called the cumulant generating functional and the centred cumulant generating functional, over a metric space of log-likelihoods and measures. The former characterises the posterior of Bayesian inference as a part of the arc gradient that induces a flow of log-likelihoods and non-negative measures. The latter characterises the difference of the posterior and the prior as a part of the arc gradient that induces a flow of log-likelihoods and probability measures. Our results reveal an implication of the belief updating mechanism from the prior to the posterior as an infinitesimal change of a measure in the infinite-dimensional Hamiltonian flows.
In this article, we explore two effective means to communicate the concept of walkability - 1) visualization, and 2) descriptive statistics. We introduce the concept of walkability as measuring the quality of an urban space based on the distance needed to walk from that space to a range of different social, environmental, and economic amenities. We use Dublin city as a worked example and explore quantification and visualization of walkability of various areas of the city. We utilize the Google Map API and Tableau to visualize the less walkable areas across Dublin city and using WLS regression, we assess the effects of unwalkability on house prices in Dublin, thus quantifying the importance of walkable areas from an economic perspective.
Efficient CI-Based One-Bit Precoding for Multiuser Downlink Massive MIMO Systems with PSK Modulation
In this paper, we consider the one-bit precoding problem for the multiuser downlink massive multiple-input multiple-output (MIMO) system with phase shift keying (PSK) modulation. We focus on the celebrated constructive interference (CI)-based problem formulation. We first establish the NP-hardness of the problem (even in the single-user case), which reveals the intrinsic difficulty of globally solving the problem. Then, we propose a novel negative $\ell_1$ penalty model for the considered problem, which penalizes the one-bit constraint into the objective by a negative $\ell_1$-norm term, and show the equivalence between (global and local) solutions of the original problem and the penalty problem when the penalty parameter is sufficiently large. We further transform the penalty model into an equivalent min-max problem and propose an efficient alternating proximal/projection gradient descent ascent (APGDA) algorithm for solving it, which performs a proximal gradient decent over one block of variables and a projection gradient ascent over the other block of variables alternately. The APGDA algorithm enjoys a low per-iteration complexity and is guaranteed to converge to a stationary point of the min-max problem and a local minimizer of the penalty problem. To further reduce the computational cost, we also propose a low-complexity implementation of the APGDA algorithm, where the values of the variables will be fixed in later iterations once they satisfy the one-bit constraint. Numerical results show that, compared to the state-of-the-art CI-based algorithms, both of the proposed algorithms generally achieve better bit-error-rate (BER) performance with lower computational cost.
In this paper, we tackle two challenges in multimodal learning for visual recognition: 1) when missing-modality occurs either during training or testing in real-world situations; and 2) when the computation resources are not available to finetune on heavy transformer models. To this end, we propose to utilize prompt learning and mitigate the above two challenges together. Specifically, our modality-missing-aware prompts can be plugged into multimodal transformers to handle general missing-modality cases, while only requiring less than 1% learnable parameters compared to training the entire model. We further explore the effect of different prompt configurations and analyze the robustness to missing modality. Extensive experiments are conducted to show the effectiveness of our prompt learning framework that improves the performance under various missing-modality cases, while alleviating the requirement of heavy model re-training. Code is available.
Temporal sentence grounding in videos (TSGV), a.k.a., natural language video localization (NLVL) or video moment retrieval (VMR), aims to retrieve a temporal moment that semantically corresponds to a language query from an untrimmed video. Connecting computer vision and natural language, TSGV has drawn significant attention from researchers in both communities. This survey attempts to provide a summary of fundamental concepts in TSGV and current research status, as well as future research directions. As the background, we present a common structure of functional components in TSGV, in a tutorial style: from feature extraction from raw video and language query, to answer prediction of the target moment. Then we review the techniques for multimodal understanding and interaction, which is the key focus of TSGV for effective alignment between the two modalities. We construct a taxonomy of TSGV techniques and elaborate methods in different categories with their strengths and weaknesses. Lastly, we discuss issues with the current TSGV research and share our insights about promising research directions.
This paper offers a comprehensive review of the research on Natural Language Generation (NLG) over the past two decades, especially in relation to data-to-text generation and text-to-text generation deep learning methods, as well as new applications of NLG technology. This survey aims to (a) give the latest synthesis of deep learning research on the NLG core tasks, as well as the architectures adopted in the field; (b) detail meticulously and comprehensively various NLG tasks and datasets, and draw attention to the challenges in NLG evaluation, focusing on different evaluation methods and their relationships; (c) highlight some future emphasis and relatively recent research issues that arise due to the increasing synergy between NLG and other artificial intelligence areas, such as computer vision, text and computational creativity.
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.
In this paper, we propose a novel Feature Decomposition and Reconstruction Learning (FDRL) method for effective facial expression recognition. We view the expression information as the combination of the shared information (expression similarities) across different expressions and the unique information (expression-specific variations) for each expression. More specifically, FDRL mainly consists of two crucial networks: a Feature Decomposition Network (FDN) and a Feature Reconstruction Network (FRN). In particular, FDN first decomposes the basic features extracted from a backbone network into a set of facial action-aware latent features to model expression similarities. Then, FRN captures the intra-feature and inter-feature relationships for latent features to characterize expression-specific variations, and reconstructs the expression feature. To this end, two modules including an intra-feature relation modeling module and an inter-feature relation modeling module are developed in FRN. Experimental results on both the in-the-lab databases (including CK+, MMI, and Oulu-CASIA) and the in-the-wild databases (including RAF-DB and SFEW) show that the proposed FDRL method consistently achieves higher recognition accuracy than several state-of-the-art methods. This clearly highlights the benefit of feature decomposition and reconstruction for classifying expressions.
In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for different languages as different tasks, and meta-learned the initialization parameters from many pretraining languages to achieve fast adaptation on unseen target language, via recently proposed model-agnostic meta learning algorithm (MAML). We evaluated the proposed approach using six languages as pretraining tasks and four languages as target tasks. Preliminary results showed that the proposed method, MetaASR, significantly outperforms the state-of-the-art multitask pretraining approach on all target languages with different combinations of pretraining languages. In addition, since MAML's model-agnostic property, this paper also opens new research direction of applying meta learning to more speech-related applications.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191