Unsupervised semantic segmentation is a challenging task that segments images into semantic groups without manual annotation. Prior works have primarily focused on leveraging prior knowledge of semantic consistency or priori concepts from self-supervised learning methods, which often overlook the coherence property of image segments. In this paper, we demonstrate that the smoothness prior, asserting that close features in a metric space share the same semantics, can significantly simplify segmentation by casting unsupervised semantic segmentation as an energy minimization problem. Under this paradigm, we propose a novel approach called SmooSeg that harnesses self-supervised learning methods to model the closeness relationships among observations as smoothness signals. To effectively discover coherent semantic segments, we introduce a novel smoothness loss that promotes piecewise smoothness within segments while preserving discontinuities across different segments. Additionally, to further enhance segmentation quality, we design an asymmetric teacher-student style predictor that generates smoothly updated pseudo labels, facilitating an optimal fit between observations and labeling outputs. Thanks to the rich supervision cues of the smoothness prior, our SmooSeg significantly outperforms STEGO in terms of pixel accuracy on three datasets: COCOStuff (+14.9%), Cityscapes (+13.0%), and Potsdam-3 (+5.7%).
Unsupervised Feature Learning by Deep Sparse Coding
Georgia Institute of Technology(佐治亚理工学院);DeepMind Technologies(DeepMind科技公司);Princeton University(普林斯顿大学);The City College of New York(纽约城市学院);University of Virginia(弗吉尼亚大学)
PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimation
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)理工学院);Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳人工智能与机器人研究院(社会))
Large Scale Unsupervised Brain MRI Image Registration Solution for Learn2Reg 2024
College of Electrical and Information Engineering, Hunan University(湖南大学电气与信息工程学院);National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University(湖南大学机器人视觉感知与控制技术国家工程研究中心)
College of Electronics and Information Engineering, Tongji University(同济大学电子信息工程学院);Harbin Institute of Technology Suzhou Research Institute(哈尔滨工业大学苏州研究院);Department of Computer Science and Technology, Tongji University(同济大学计算机科学与技术系);Multimedia Technology and Telecom Department, Telecommunications Center, Moscow Institute of Physics(莫斯科物理技术学院多媒体技术与电信系、电信中心)
Unsupervised Deformable Image Registration with Structural Nonparametric Smoothing
Cornell University(康奈尔大学);Hunan University(湖南大学);University of Pennsylvania(宾夕法尼亚大学);Johns Hopkins University(约翰霍普金斯大学);Shanghai Jiao Tong University(上海交通大学);University of Birmingham(伯明翰大学);University of Manchester(曼彻斯特大学)
Low-Rank Velocity Fields as a Structural Prior for Unsupervised 4D Medical Image Interpolation
Southern University of Science and Technology(南方科技大学);Shenzhen University of Advanced Technology(深圳先进技术研究院);Shenzhen University Medical School(深圳大学医学院);Shenzhen University(深圳大学);Research Institute of Trustworthy Autonomous Systems(可信自主系统研究院)
Eliminating Warping Shakes for Unsupervised Online Video Stitching
Institute of Information Science, Beijing Jiaotong University(北京交通大学信息科学研究所);Nanyang Technological University(南洋理工大学);Communication University of Zhejiang(浙江传媒学院);University of Electronic Science and Technology of China(电子科技大学)
Shanghai Research Institute for Intelligent Autonomous Systems(上海智能自主系统研究院);Shanghai Institute of Intelligent Science and Technology(上海智能科学技术研究院);State Key Laboratory of Intelligent Autonomous Systems(智能自主系统国家重点实验室);Frontiers Science Center for Intelligent Autonomous Systems(智能自主系统前沿科学中心)
StabStitch++: Unsupervised Online Video Stitching with Spatiotemporal Bidirectional Warps
Institute of Information Science, Beijing Jiaotong University(北京交通大学信息科学学院);Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing(教育部视觉智能+X国际合作联合实验室);School of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院);School of Media Engineering, Communication University of Zhejiang(浙江传媒学院媒体工程学院);School of Information and Communication Engineering, University of Electronic Science and Technology of China(电子科技大学信息与通信工程学院)
LEGO: Learning Edge with Geometry all at Once by Watching Videos
University of Southern California(南加州大学);Baidu Research(百度研究院);National Engineering Laboratory for Deep Learning Technology and Applications(深度学习技术及应用国家工程实验室)