Filters








2,542 Hits in 6.1 sec

Improving Semantic Segmentation via Video Propagation and Label Relaxation [article]

Yi Zhu, Karan Sapra, Fitsum A. Reda, Kevin J. Shih, Shawn Newsam, Andrew Tao, Bryan Catanzaro
2019 arXiv   pre-print
Furthermore, we introduce a novel boundary label relaxation technique that makes training robust to annotation noise and propagation artifacts along object boundaries.  ...  In this paper, we present a video prediction-based methodology to scale up training sets by synthesizing new training samples in order to improve the accuracy of semantic segmentation networks.  ...  Acknowledgements We would like to thank Saad Godil, Matthieu Le, Ming-Yu Liu and Guilin Liu for suggestions and discussions.  ... 
arXiv:1812.01593v3 fatcat:4n4g3e7ks5d7nmuti2y3e5jknu

Weakly-Supervised Video Scene Co-parsing [chapter]

Guangyu Zhong, Yi-Hsuan Tsai, Ming-Hsuan Yang
2017 Lecture Notes in Computer Science  
To exploit rich semantic information, we first collect all videos that share the same video-level labels and segment them into supervoxels.  ...  In this paper, we propose a scene co-parsing framework to assign pixel-wise semantic labels in weakly-labeled videos, i.e., only videolevel category labels are given.  ...  This work is supported in part by the NSF CAREER grant #1149783, NSF IIS grant #1152576, and gifts from Adobe and Nvidia. G. Zhong is sponsored by China Scholarship Council and NSFC grant #61572099.  ... 
doi:10.1007/978-3-319-54181-5_2 fatcat:tatumyvxffb3rilyf5g4ek7vem

Semantic Segmentation for Aerial Images: A Literature Review

Yongki Christian Sanjaya, Alexander Agung Santoso Gunawan, Edy Irwansyah
2020 Engineering, Mathematics and Computer Science Journal (EMACS)  
Segmentation, and can also be used as a reference for developing new Semantic Image Segmentation models in the future  ...  Due to this rapid growth, many models related to Semantic Image Segmentation have been produced and have also been used or applied in many domains such as medical areas and intelligent transportation.  ...  Improving Semantic Segmentation via Video Propagation and Label Relaxation This model proposes the use of the DeepLabV3Plus + SDCNetAug [14] method to solve the semantic image segmentation problem.  ... 
doi:10.21512/emacsjournal.v2i3.6737 fatcat:5zncush42bbj7lrckjpfn34nsu

Semantic object segmentation via detection in weakly labeled video

Yu Zhang, Xiaowu Chen, Jia Li, Chen Wang, Changqun Xia
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
To address this problem, this paper proposes an approach to segment semantic objects in weakly labeled video via object detection.  ...  In many cases, however, semantic objects are only tagged at video-level, making them difficult to be located and segmented.  ...  This work is supported in part by grants from NSFC (61325011), 863 program (2013AA013801), and SRFDP (20131102130002).  ... 
doi:10.1109/cvpr.2015.7298987 dblp:conf/cvpr/ZhangCLWX15 fatcat:65bkleamgza3hah5m5ujdq5dsm

Titelei/Inhaltsverzeichnis [chapter]

Matthias Reso
2018 Temporally Consistent Superpixels  
This thesis addresses the field of early stage video preprocessing in order to improve and accelerate subsequent processing steps like semantic video segmentation or video-based object tracking.  ...  A framework is proposed to segment video streams into temporally consistent superpixels in order to create a representation of the video with far less image primitives than the voxelgrid.  ...  This thesis addresses the field of early stage video preprocessing in order to improve and accelerate subsequent processing steps like semantic video segmentation or video-based object tracking.  ... 
doi:10.51202/9783186861108-i fatcat:my6gxunipngbhazxexzaxuofea

Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction [article]

Wonkwang Lee, Whie Jung, Han Zhang, Ting Chen, Jing Yu Koh, Thomas Huang, Hyungsuk Yoon, Honglak Lee, Seunghoon Hong
2021 arXiv   pre-print
Our method predicts future frames by first estimating a sequence of semantic structures and subsequently translating the structures to pixels by video-to-video translation.  ...  Full videos and codes are available at https://1konny.github.io/HVP/.  ...  Newsam, Andrew Tao, and Bryan Catanzaro. Improving semantic segmentation via video propagation and label relaxation. In CVPR, 2019. Nevan Wichers, Ruben Villegas, Dumitru Erhan, and Honglak Lee.  ... 
arXiv:2104.06697v1 fatcat:thkaq2a53fhyzedof52lzw7xtm

Multi-view Dense Depth Map Estimation

Cevahir Çigla, A. Aydin Alatan
2009 Proceedings of the 2nd International ICST Conference on Immersive Telecommunications  
Markov Random Field (MRF) modeling is utilized for each view in pixel-wise manner in order to relax and refine the estimated planar models while incorporating visibility and consistency constraints.  ...  Hence, extraction of multiple depth maps is achieved from multi-view video.  ...  In the second step, in order to improve the depth estimate accuracy, the planarity assumption is relaxed by modeling each image as MRF and utilizing pixel-based belief propagation that takes into account  ... 
doi:10.4108/icst.immerscom2009.6223 dblp:conf/immerscom/CiglaA09 fatcat:vhswacvipvgdhe5e3csrsxtz7a

Accelerated Inference in Markov Random Fields via Smooth Riemannian Optimization [article]

Siyi Hu, Luca Carlone
2018 arXiv   pre-print
We demonstrate the proposed approaches in multi-class image segmentation problems.  ...  The backbone of this second approach is a novel SDP relaxation combined with a fast and scalable solver based on smooth Riemannian optimization.  ...  Semantic Segmentation. Semantic segmentation methods assign a semantic label to each "region" in an RBG image (2D segmentation), RBG-D image, or 3D model (3D segmentation).  ... 
arXiv:1810.11689v2 fatcat:gdjhdobz4vbzbc5gazloq53lui

Structured Consistency Loss for semi-supervised semantic segmentation [article]

Jongmok Kim, Jooyoung Jang, Hyunwoo Park, SeongAh Jeong
2021 arXiv   pre-print
This ranks the first place on the pixel-level semantic labeling task of Cityscapes benchmark suite.  ...  To the best of our knowledge, we are the first to present the superiority of state-of-the-art semi-supervised learning in semantic segmentation.  ...  [29] presents the inspiring improvement of results thanks to labelling of video image using temporal information, boundary relaxation loss to address the boundary issue and class uniform sampling for  ... 
arXiv:2001.04647v2 fatcat:4btrclnqs5hj3nk5di6ydh7kpa

Joint-task Self-supervised Learning for Temporal Correspondence [article]

Xueting Li, Sifei Liu, Shalini De Mello, Xiaolong Wang, Jan Kautz, Ming-Hsuan Yang
2019 arXiv   pre-print
Our method outperforms the state-of-the-art self-supervised methods on a variety of visual correspondence tasks, including video-object and part-segmentation propagation, keypoint tracking, and object  ...  Our learning process integrates two highly related tasks: tracking large image regions and establishing fine-grained pixel-level associations between consecutive video frames.  ...  For the semantic propagation task, we propagate the semantic segmentation maps of human parts (e.g., arms and legs) and evaluate performance via the mean IoU metric.  ... 
arXiv:1909.11895v1 fatcat:g6nxl6dvcfcz5l6hmvlxdxbqqa

RGPNet: A Real-Time General Purpose Semantic Segmentation [article]

Elahe Arani, Shabbir Marzban, Andrei Pata, Bahram Zonooz
2020 arXiv   pre-print
We propose a real-time general purpose semantic segmentation architecture, RGPNet, which achieves significant performance gain in complex environments.  ...  Moreover, towards green AI, we show that using an optimized label-relaxation technique with progressive resizing can reduce the training time by up to 60% while preserving the performance.  ...  Progressive resizing with label relaxation In order to validate the gain from label relaxation, we compare the result of progressive resizing training with and without label relaxation.  ... 
arXiv:1912.01394v2 fatcat:ycxneyuqk5ejrjo3jg4tfbag44

A Generic Framework for Video Annotation via Semi-Supervised Learning

Tianzhu Zhang, Changsheng Xu, Guangyu Zhu, Si Liu, Hanqing Lu
2012 IEEE transactions on multimedia  
., sports, news, and movies), is proposed to jointly explore small-scale expert labeled videos and large-scale unlabeled videos to train the models.  ...  The expert labeled videos are obtained from the analysis and alignment of well-structured video related text (e.g., movie scripts, web-casting text, close caption).  ...  Therefore, interesting events in a video can be localized and video can be segmented with its semantic concept. 3) Semantic Search and Navigation: Based on event detection (event recognition and localization  ... 
doi:10.1109/tmm.2012.2191944 fatcat:7uaujwzq4nfrto5jaim7bf4ify

Panoptic-DeepLab [article]

Bowen Cheng and Maxwell D. Collins and Yukun Zhu and Ting Liu and Thomas S. Huang and Hartwig Adam and Liang-Chieh Chen
2019 arXiv   pre-print
In particular, we adopt the dual-ASPP and dual-decoder structures specific to semantic, and instance segmentation, respectively.  ...  The semantic segmentation branch is the same as the typical design of any semantic segmentation model (e.g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance  ...  Improving semantic segmentation via video propagation and label relaxation. In CVPR, 2019. 4  ... 
arXiv:1910.04751v3 fatcat:r24vr6366ffydhzg2cur5gkz7i

SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency [article]

Devendra Singh Chaplot, Murtaza Dalal, Saurabh Gupta, Jitendra Malik, Ruslan Salakhutdinov
2021 arXiv   pre-print
The semantic map is used to compute an intrinsic motivation reward for training the exploration policy and for labelling the agent observations using spatio-temporal 3D consistency and label propagation  ...  The observations gathered by this exploration policy are labelled using 3D consistency and used to improve the perception model.  ...  Acknowledgements Carnegie Mellon University effort was supported in part by the US Army Grant W911NF1920104 and DSTA. UIUC effort is partially funded by NASA Grant 80NSSC21K1030.  ... 
arXiv:2112.01001v1 fatcat:5vvysf4wjvc5pptvdtkvjqkmne

Weighted Intersection over Union (wIoU): A New Evaluation Metric for Image Segmentation [article]

Yeong-Jun Cho
2021 arXiv   pre-print
The goal of semantic segmentation is to assign a class label of each pixel in the scene.  ...  In this paper, we propose a novel evaluation metric for performance evaluation of semantic segmentation.  ...  Tao, and B. Catanzaro. Improving semantic segmentation via video propagation and label relaxation.  ... 
arXiv:2107.09858v1 fatcat:dmwrsh5hovfszcr2cyxaibqqa4
« Previous Showing results 1 — 15 out of 2,542 results