ACM Computing Surveys最新文献

In the past few years, Differentiable Neural Architecture Search (DNAS) rapidly imposed itself as the trending approach to automate the discovery of deep neural network architectures. This rise is mainly due to the popularity of DARTS (Differentiable ARchitecTure Search), one of the first major DNAS methods. In contrast with previous works based on Reinforcement Learning or Evolutionary Algorithms, DNAS is faster by several orders of magnitude and uses fewer computational resources. In this comprehensive survey, we focused specifically on DNAS and reviewed recent approaches in this field. Furthermore, we proposed a novel challenge-based taxonomy to classify DNAS methods. We also discussed the contributions brought to DNAS in the past few years and its impact on the global NAS field. Finally, we concluded by giving some insights into future research directions for the DNAS field.

Privacy-enhancing technologies are technologies that implement fundamental data protection principles. With respect to biometric recognition, different types of privacy-enhancing technologies have been introduced for protecting stored biometric data which are generally classified as sensitive. In this regard, various taxonomies and conceptual categorizations have been proposed and standardisation activities have been carried out. However, these efforts have mainly been devoted to certain sub-categories of privacy-enhancing technologies and therefore lack generalization. This work provides an overview of concepts of privacy-enhancing technologies for biometric recognition in a unified framework. Key properties and differences between existing concepts are highlighted in detail at each processing step. Fundamental characteristics and limitations of existing technologies are discussed and related to data protection techniques and principles. Moreover, scenarios and methods for the assessment of privacy-enhancing technologies for biometric recognition are presented. This paper is meant as a point of entry to the field of data protection for biometric recognition applications and is directed towards experienced researchers as well as non-experts.

Aerial object detection, as object detection in aerial images captured from an overhead perspective, has been widely applied in urban management, industrial inspection, and other aspects. However, the performance of existing aerial object detection algorithms is hindered by variations in object scales and orientations attributed to the aerial perspective. This survey presents a comprehensive review of recent advances in aerial object detection. We start with some basic concepts of aerial object detection and then summarize the five imbalance problems of aerial object detection, including scale imbalance, spatial imbalance, objective imbalance, semantic imbalance, and class imbalance. Moreover, we classify and analyze relevant methods and especially introduce the applications of aerial object detection in practical scenarios. Finally, the performance evaluation is presented on two popular aerial object detection datasets VisDrone-DET and DOTA, and we discuss several future directions that could facilitate the development of aerial object detection.

In the field of Sequential Decision Making (SDM), two paradigms have historically vied for supremacy: Automated Planning (AP) and Reinforcement Learning (RL). In the spirit of reconciliation, this paper reviews AP, RL and hybrid methods (e.g., novel learn to plan techniques) for solving Sequential Decision Processes (SDPs), focusing on their knowledge representation: symbolic, subsymbolic or a combination. Additionally, it also covers methods for learning the SDP structure. Finally, we compare the advantages and drawbacks of the existing methods and conclude that neurosymbolic AI poses a promising approach for SDM, since it combines AP and RL with a hybrid knowledge representation.

Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing. While there have been remarkable improvements in model accuracy, deploying these models on lightweight devices, such as mobile phones and microcontrollers, is constrained by limited resources. In this survey, we provide comprehensive design guidance tailored for these devices, detailing the meticulous design of lightweight models, compression methods, and hardware acceleration strategies. The principal goal of this work is to explore methods and concepts for getting around hardware constraints without compromising the model’s accuracy. Additionally, we explore two notable paths for lightweight deep learning in the future: deployment techniques for TinyML and Large Language Models. Although these paths undoubtedly have potential, they also present significant challenges, encouraging research into unexplored areas.

Deep learning approaches have achieved great success in the field of Natural Language Processing (NLP). However, directly training deep neural models often suffer from overfitting and data scarcity problems that are pervasive in NLP tasks. In recent years, Multi-Task Learning (MTL), which can leverage useful information of related tasks to achieve simultaneous performance improvement on these tasks, has been used to handle these problems. In this paper, we give an overview of the use of MTL in NLP tasks. We first review MTL architectures used in NLP tasks and categorize them into four classes, including parallel architecture, hierarchical architecture, modular architecture, and generative adversarial architecture. Then we present optimization techniques on loss construction, gradient regularization, data sampling, and task scheduling to properly train a multi-task model. After presenting applications of MTL in a variety of NLP tasks, we introduce some benchmark datasets. Finally, we make a conclusion and discuss several possible research directions in this field.

The paper reviews methods used in the fashion compatibility recommendation domain. We select methods based on reproducibility, explainability, and novelty aspects and then organize them chronologically and thematically. We presented general characteristics of publicly available datasets that are related to the fashion compatibility recommendation task. Finally, we analyzed the representation bias of datasets, fashion-based algorithms’ sustainability, and explainable model assessment. The paper describes practical problem explanations, methodologies, and published datasets that may serve as an inspiration for further research. The proposed structure of the survey organizes knowledge in the fashion recommendation domain and will be beneficial for those who want to learn the topic from scratch, expand their knowledge, or find a new field for research. Furthermore, the information included in this paper could contribute to developing an effective and ethical fashion-based recommendation system.

There is a growing interest in the area of machine learning and creativity. This survey presents an overview of the history and the state of the art of computational creativity theories, key machine learning techniques (including generative deep learning), and corresponding automatic evaluation methods. After presenting a critical discussion of the key contributions in this area, we outline the current research challenges and emerging opportunities in this field.

This survey paper proposes a clearer view of natural language reasoning in the field of Natural Language Processing (NLP), both conceptually and practically. Conceptually, we provide a distinct definition for natural language reasoning in NLP, based on both philosophy and NLP scenarios, discuss what types of tasks require reasoning, and introduce a taxonomy of reasoning. Practically, we conduct a comprehensive literature review on natural language reasoning in NLP, mainly covering classical logical reasoning, natural language inference, multi-hop question answering, and commonsense reasoning. The paper also identifies and views backward reasoning, a powerful paradigm for multi-step reasoning, and introduces defeasible reasoning as one of the most important future directions in natural language reasoning research. We focus on single-modality unstructured natural language text, excluding neuro-symbolic research and mathematical reasoning.

Deep-learning (DL) performs well in computer-vision and medical-imaging automated decision-making applications. A bottleneck of DL stems from the large amount of labelled data required to train accurate models that generalise well. Data scarcity and imbalance are common problems in imaging applications that can lead DL models towards biased decision making. A solution to this problem is synthetic data. Synthetic data is an inexpensive substitute to real data for improved accuracy and generalisability of DL models. This survey reviews the recent methods published in relation to the creation and use of synthetic data for computer-vision and medical-imaging DL applications. The focus will be on applications that utilised synthetic data to improve DL models by either incorporating an increased diversity of data that is difficult to obtain in real life, or by reducing a bias caused by class imbalance. Computer-graphics software and generative networks are the most popular data generation techniques encountered in the literature. We highlight their suitability for typical computer-vision and medical-imaging applications, and present promising avenues for research to overcome their computational and theoretical limitations.