开放世界物体识别与检测系统:现状、挑战与展望  

Open World Object Recognition and Detection Systems:Landscapes,Challenges and Prospects

作　　者：聂晖 王瑞平[1,2] 陈熙霖 Nie Hui;Wang Ruiping;Chen Xilin(Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190;University of Chinese Academy of Sciences,Beijing 100049)

机构地区：[1]中国科学院计算技术研究所,北京100190 [2]中国科学院大学,北京100049

出　　处：《计算机研究与发展》2024年第9期2128-2141,共14页Journal of Computer Research and Development

基　　金：科技创新2030—“新一代人工智能”重大项目(2021ZD0111901);国家自然科学基金项目(U21B2025,U19B2036)。

摘　　要：探究了从封闭环境到开放世界环境的转变及其对视觉感知(集中于物体识别和检测)与深度学习领域的影响.在开放世界环境中,系统软件需适应不断变化的环境和需求,这为深度学习方法带来新挑战.特别是,开放世界视觉感知要求系统理解和处理训练阶段未见的环境和物体,这超出了传统封闭系统的能力.首先讨论了技术进步带来的动态、自适应系统需求,突出了开放系统相较封闭系统的优势.接着,深入探讨了开放世界的定义和现有工作,涵盖开集学习、零样本学习、小样本学习、长尾学习、增量学习等5个开放维度.在开放世界物体识别方面,分析了每个维度的核心挑战,并为每个任务数据集提供了量化的评价指标.对于开放世界物体检测,讨论了检测相比识别的新增挑战,如遮挡、尺度、姿态、共生关系、背景干扰等,并强调了仿真环境在构建开放世界物体检测数据集中的重要性.最后,强调开放世界概念为深度学习带来的新视角和机遇,是推动技术进步和深入理解世界的机会,为未来研究提供参考.We explore the transition from closed environments to open world environments and its impact on visual perception(focusing on object recognition and detection)and the field of deep learning.In open world environments,software systems need to adapt to constantly changing conditions and demands,presenting new challenges for deep learning methods.In particular,open world visual perception requires systems to understand and process environments and objects not seen during the training phase,which exceeds the capabilities of traditional closed systems.We first discuss the dynamic and adaptive system requirements brought about by technological advances,highlighting the advantages of open systems over closed systems.Then we delve into the definition of the open world and existing work,covering five dimensions of openness:open set learning,zero-shot learning,few-shot learning,long-tail learning,and incremental learning.In terms of open world recognition,we analyze the core challenges of each dimension and provide quantified evaluation metrics for each task dataset.For open world object detection,we discuss additional challenges compared with recognition,such as occlusion,scale,posture,symbiotic relationships,background interference,etc.,and emphasize the importance of simulation environments in constructing open world object detection datasets.Finally,we underscore the new perspectives and opportunities that the concept of the open world brings to deep learning,acting as a catalyst for technological advancement and deeper understanding of the realistic environment challenges,offering a reference for future research.

关 键 词：开放世界 视觉感知 物体检测 物体识别 评价指标 仿真环境 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]