VALSE 论文速览 第136期：通用实例感知作为物体发现与检索

论文题目：Universal Instance Perception as Object Discovery and Retrieval

作者列表：

严彬 (大连理工大学)，江毅 (字节跳动)，吴剑南 (香港大学)，王栋 (大连理工大学)，罗平 (香港大学)，袁泽寰 (字节跳动)，卢湖川 (大连理工大学)

B站观看网址：

https://www.bilibili.com/video/BV15H4y1o7jz/

论文摘要：

All instance perception tasks aim at finding certain objects specified by some queries such as category names, language expressions, and target annotations, but this complete field has been split into multiple independent subtasks. In this work, we present a universal instance perception model of the next generation, termed UNINEXT. UNINEXT reformulates diverse instance perception tasks into a unified object discovery and retrieval paradigm and can flexibly perceive different types of objects by simply changing the input prompts. This unified formulation brings the following benefits: (1) enormous data from different tasks and label vocabularies can be exploited for jointly training general instance-level representations, which is especially beneficial for tasks lacking in training data. (2) the unified model is parameter-efficient and can save redundant computation when handling multiple tasks simultaneously. UNINEXT shows superior performance on 20 challenging benchmarks from 10 instance-level tasks including classical image-level tasks (object detection and instance segmentation), vision-and-language tasks (referring expression comprehension and segmentation), and six video-level object tracking tasks. Code is available at https://github.com/MasterBin-IIAU/UNINEXT.

论文信息：

[1] Bin Yan, Yi Jiang, Jiannan Wu, Dong Wang, Ping Luo, Zehuan Yuan, Huchuan Lu, Universal Instance Perception as Object Discovery and Retrieval, In CVPR, 2023.

论文链接：

[https://arxiv.org/abs/2303.06674]

代码链接：

[https://github.com/MasterBin-IIAU/UNINEXT]

视频讲者简介：

严彬，大连理工大学在读博士，研究方向为目标跟踪与实例感知，导师是卢湖川教授。作为第一作者在CVPR，ICCV，ECCV等计算机视觉领域顶级会议上发表论文多篇，曾获研究生国家奖学金，研究生学术之星，CCF-CV学术新锐奖等荣誉。

特别鸣谢本次论文速览主要组织者：

月度轮值AC：焦剑波 (伯明翰大学)

季度轮值AC：叶茫 (武汉大学)