Filters








3,209 Hits in 7.0 sec

Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection [article]

Zhongzheng Ren, Zhiding Yu, Xiaodong Yang, Ming-Yu Liu, Yong Jae Lee, Alexander G. Schwing, Jan Kautz
2020 arXiv   pre-print
To target these issues we develop an instance-aware and context-focused unified framework.  ...  It employs an instance-aware self-training algorithm and a learnable Concrete DropBlock while devising a memory-efficient sequential batch back-propagation.  ...  To address the mentioned three challenges caused by this ambiguity, we develop the instance-aware and context-focused framework outlined in Fig. 2 .  ... 
arXiv:2004.04725v3 fatcat:m54u6bitpzcxbgobl5sdyauj4m

Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object Detection

Zhongzheng Ren, Zhiding Yu, Xiaodong Yang, Ming-Yu Liu, Yong Jae Lee, Alexander G. Schwing, Jan Kautz
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
To target these issues we develop an instance-aware and context-focused unified framework.  ...  In addition, the proposed method is the first to benchmark ResNet based models and weakly supervised video object detection.  ...  To address the above three challenges, we propose a unified weakly supervised learning framework that is instanceaware and context-focused.  ... 
doi:10.1109/cvpr42600.2020.01061 dblp:conf/cvpr/RenYY0LSK20 fatcat:pf7lnl2tnjfcjpnrwzdlkiseyi

Semi-global Context Network for Semantic Correspondence

Ho-Jun Lee, Hong Tae Choi, Sung Kyu Park, Ho-Hyun Park
2020 IEEE Access  
We introduce a global context fused feature representation that efficiently employs the global semantic context in estimating semantic correspondence as well as a semi-global self-similarity feature to  ...  INDEX TERMS Context fusion, historical averaging, neighborhood consensus network, semantic correspondence, semi-global self-similarity, weakly supervised learning. 2496 This work is licensed under a Creative  ...  computer vision tasks such as image editing, scene understanding, object tracking, object detection, and 3D reconstruction.  ... 
doi:10.1109/access.2020.3046845 fatcat:wzikdaus75fxxcfhw7ze6b3nca

Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation [article]

Tianfei Zhou, Meijie Zhang, Fang Zhao, Jianwu Li
2022 arXiv   pre-print
to gather diverse relational contexts in the memory to enrich semantic representations.  ...  Our work alleviates this from a novel perspective, by exploring rich semantic contexts synergistically among abundant weakly-labeled training data for network learning and inference.  ...  tasks (e.g., semantic segmentation, object detection).  ... 
arXiv:2203.09653v2 fatcat:qzlrq4o4enafpoctphmqn6e7bu

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision [article]

Shiyi Lan, Zhiding Yu, Christopher Choy, Subhashree Radhakrishnan, Guilin Liu, Yuke Zhu, Larry S. Davis, Anima Anandkumar
2021 arXiv   pre-print
Our best model achieves 37.9% AP on COCO instance segmentation, surpassing prior weakly supervised methods and is competitive to supervised methods.  ...  Minimizing the teacher energy simultaneously yields refined object masks and dense correspondences between intra-class objects, which are taken as pseudo-labels to supervise the task network and provide  ...  Efficient- Det: Scalable and efficient object detection.  ... 
arXiv:2105.06464v2 fatcat:wr5iyiqvivb3novhhkgxwk6mv4

A Survey of Visual Sensory Anomaly Detection [article]

Xi Jiang, Guoyang Xie, Jinbao Wang, Yong Liu, Chengjie Wang, Feng Zheng, Yaochu Jin
2022 arXiv   pre-print
Furthermore, we classify each kind of anomaly according to the level of supervision. Finally, we summarize the challenges and provide open directions for this community.  ...  Compared with semantic anomaly detection which detects anomaly at the label level (semantic shift), visual sensory AD detects the abnormal part of the sample (covariate shift).  ...  [ 2021] apply GAN into the context of abnormal event detection. Furthermore, the authors focus on object detection, which could be more general and background agnostic.  ... 
arXiv:2202.07006v1 fatcat:2bqzmmrnjzggti5tcewa3mh3sa

A Survey on Deep Learning Technique for Video Segmentation [article]

Wenguan Wang, Tianfei Zhou, Fatih Porikli, David Crandall, Luc Van Gool
2021 arXiv   pre-print
In this survey, we comprehensively review two basic lines of research - generic object segmentation (of unknown categories) in videos and video semantic segmentation - by introducing their respective task  ...  settings, background concepts, perceived need, development history, and main challenges.  ...  , unsupervised, and weakly supervised learning based. • Supervised Learning based Methods.  ... 
arXiv:2107.01153v3 fatcat:nry4yjhq7zhtzbfh53wf7ie3um

Location-Aware Image Classification [chapter]

Xinggang Wang, Xin Yang, Wenyu Liu, Chen Duan, Longin Jan Latecki
2016 Lecture Notes in Computer Science  
In our framework, an image is classified based on local image representation, and the classifier is learned using an iterative multi-instance learning with a latent SVM, i.e., we infer object location  ...  Our method is very efficient and outperforms the popular spatial pyramid matching (SPM) method and the Region Based Latent SVM (RBLSVM) method [1] on the challenging PASCAL VOC dataset.  ...  IIS-1302164 and OIA-1027897.  ... 
doi:10.1007/978-3-319-27671-7_69 fatcat:eg6jujr5pzakzcg4pajvcb3tw4

Salient Instance Segmentation with Region and Box-level Annotations [article]

Jialun Pei, He Tang, Tianyang Cheng, Chuanbo Chen
2021 arXiv   pre-print
object detection datasets.  ...  To this end, we present a cyclic global context salient instance segmentation network (CGCNet), which is supervised by the combination of salient regions and bounding boxes from the ready-made salient  ...  Many weakly supervised principles have been introduced in computer vision area, including object detection, instance segmentation and saliency detection [39] , [40] .  ... 
arXiv:2008.08246v3 fatcat:e7jpm2xcrrgw5kj3oqgrww7jqi

Towards holistic scene understanding: Semantic segmentation and beyond [article]

Panagiotis Meletis
2022 arXiv   pre-print
This task combines scene and parts-level semantics with instance-level object detection.  ...  Chapter 3 focuses on enriching semantic segmentation with weak supervision and proposes a weakly-supervised algorithm for training with bounding box-level and image-level supervision instead of only with  ...  Finalizing my PhD and looking back at my life as a researcher, I have only beautiful memories and experiences to think of.  ... 
arXiv:2201.07734v1 fatcat:qdqnjqn75rff7kyja2iwer75my

Survey on Semantic Segmentation using Deep Learning Techniques

Fahad Lateef, Yassine Ruichek
2019 Neurocomputing  
Finally, we conclude by discussing some of the open problems and their possible solutions.  ...  Moreover, we focus on some of the methods and look closely at their architectures in order to find out how they have achieved their reported performances.  ...  ACKNOWLEDGMENT The authors express their gratitude to University Technology Belfort-Montbeliard and Higher Education Commission of Pakistan for providing the support and necessary requirement for completion  ... 
doi:10.1016/j.neucom.2019.02.003 fatcat:aelsfl7unvdw5j2rtyqhtgqrsm

Towards Automatic Report Generation in Spine Radiology Using Weakly Supervised Framework [chapter]

Zhongyi Han, Benzheng Wei, Stephanie Leung, Jonathan Chung, Shuo Li
2018 Lecture Notes in Computer Science  
The weakly supervised framework using object level annotations without requiring radiologist-level report annotations to generate unified reports.  ...  We show that this can be achieved via a weakly supervised framework that combines deep learning and symbolic program synthesis theory to overcome four inevitable tasks: semantic segmentation, radiological  ...  Discussion and Conclusion We show that using the weakly supervised framework that combines deep learning and symbolic program synthesis is very efficient and flexible to generate spinal radiological reports  ... 
doi:10.1007/978-3-030-00937-3_22 fatcat:dcikg4s74bhkfmhxnqdt6673xu

Active Learning Strategies for Weakly-supervised Object Detection [article]

Huy V. Vo, Oriane Siméoni, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Jean Ponce
2022 arXiv   pre-print
Fast RCNN by over 70%, showing a good trade-off between performance and data efficiency.  ...  Experiments on the VOC07 and COCO benchmarks show that BiB outperforms other active learning techniques and significantly improves the base weakly-supervised detector's performance with only a few fully-annotated  ...  .: Instanceaware, context-focused, and memory-efficient weakly supervised object detection.  ... 
arXiv:2207.12112v1 fatcat:oyidtfzyrnamdovja5t3wjxpg4

Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos [article]

Jie Wu, Guanbin Li, Xiaoguang Han, Liang Lin
2020 arXiv   pre-print
This refinement scheme completely abandons traditional sliding window based solution pattern and contributes to acquiring more efficient, boundary-flexible and content-aware grounding results.  ...  Extensive experiments on two public benchmarks Charades-STA and ActivityNet demonstrate that BAR outperforms the state-of-the-art weakly-supervised method and even beats some competitive fully-supervised  ...  [31] proposed a weakly supervised collaborative learning framework to resolve the task of weakly supervised object detection, which only requires image-level labels. In the video domain, Duan et al  ... 
arXiv:2009.08614v1 fatcat:kbb5c5y2bjbhhjvfrgrnotkkla

Salient Object Detection Techniques in Computer Vision—A Survey

Ashish Kumar Gupta, Ayan Seal, Mukesh Prasad, Pritee Khanna
2020 Entropy  
Relevant saliency modeling trends with key issues, core techniques, and the scope for future research work have been discussed in the context of difficulties often faced in salient object detection.  ...  A large number of salient object detection (SOD) methods have been devised to effectively mimic the capability of the human visual system to detect the salient regions in images.  ...  Images with salient objects are annotated to provide instance-level supervision, and information related to object category and challenging attributes. Zeng et al.  ... 
doi:10.3390/e22101174 pmid:33286942 pmcid:PMC7597345 fatcat:3p5d2nal4vhxbi2via3g7oicga
« Previous Showing results 1 — 15 out of 3,209 results