請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88148
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 陳祝嵩 | zh_TW |
dc.contributor.advisor | Chu-Song Chen | en |
dc.contributor.author | 謝宇星 | zh_TW |
dc.contributor.author | Yu-Hsing Hsieh | en |
dc.date.accessioned | 2023-08-08T16:30:48Z | - |
dc.date.available | 2023-11-10 | - |
dc.date.copyright | 2023-08-08 | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-07-12 | - |
dc.identifier.citation | J. Ahn, S. Cho, and S. Kwak. Weakly supervised learning of instance segmentation with interpixel relations. In CVPR, pages 2204–2213, 2019.
R. Aljundi, F. Babiloni, M. Elhoseiny, M. Rohrbach, and T. Tuytelaars. Memory aware synapses: Learning what (not) to forget. In ECCV, pages 139–154, 2018. R. Aljundi, P. Chakravarty, and T. Tuytelaars. Expert gate: Lifelong learning with a network of experts. In CVPR, pages 3366–3375, 2017. N. Araslanov and S. Roth. Singlestage semantic segmentation from image labels. In CVPR, pages 4252–4261, 2020. A. Arun, C. V. Jawahar, and M. P. Kumar. Weakly supervised instance segmentation by learning annotation consistent instances. In ECCV, pages 254–270, 2020. E. Belouadah and A. Popescu. Il2m: Class incremental learning with dual memory. In ICCV, October 2019. D. Biertimpel, S. Shkodrani, A. S. Baslamisli, and N. Baka. Prior to segment: Foreground cues for weakly annotated classes in partially supervised instance segmentation. In ICCV, pages 2824–2833, 2021. H. Bilen and A. Vedaldi. Weakly supervised deep detection networks. In CVPR, pages 2846–2854, 2016. D. Bolya, C. Zhou, F. Xiao, and Y. J. Lee. YOLACT++ better realtime instance segmentation. IEEE TPAMI, 44(2):1108–1121, 2022. H. Cao, Y. Wang, J. Chen, D. Jiang, X. Zhang, Q. Tian, and M. Wang. Swinunet: Unetlike pure transformer for medical image segmentation. In ECCV workshop, pages 205–218. Springer, 2022. F. Cermelli, D. Fontanel, A. Tavera, M. Ciccone, and B. Caputo. Incremental learning in semantic segmentation from image labels. In CVPR, pages 4361–4371, 2022. F. Cermelli, A. Geraci, D. Fontanel, and B. Caputo. Modeling missing annotations for incremental learning in object detection. In CVPR workshop, pages 3699–3709, 2022. F. Cermelli, M. Mancini, S. Rota Bulò, E. Ricci, and B. Caputo. Modeling the background for incremental learning in semantic segmentation. In CVPR, pages 9230–9239, 2020. S. Cha, B. Kim, Y. Yoo, and T. Moon. SSUL: Semantic segmentation with unknown label for exemplarbased classincremental learning. In NeurIPS, pages 10919–10930, 2021. A. Chattopadhay, A. Sarkar, P. Howlader, and V. N. Balasubramanian. Gradcam++: Generalized gradientbased visual explanations for deep convolutional networks. In WACV, pages 839–847, 2018. A. Chaudhry, P. K. Dokania, T. Ajanthan, and P. H. Torr. Riemannian walk for incremental learning: Understanding forgetting and intransigence. In ECCV, pages 532–547, 2018. L.C. Chen, G. Papandreou, F. Schroff, and H. Adam. Rethinking atrous convolution for semantic image segmentation. arXiv, 2017. T. Chen, S. Kornblith, M. Norouzi, and G. Hinton. A simple framework for contrastive learning of visual representations. In ICML, pages 1597–1607, 2020. B. Cheng, M. D. Collins, Y. Zhu, T. Liu, T. S. Huang, H. Adam, and L.C. Chen. PanopticDeepLab: A simple, strong, and fast baseline for bottomup panoptic segmentation. In CVPR, pages 12472–12482, 2020. M. Delange, R. Aljundi, M. Masana, S. Parisot, X. Jia, A. Leonardis, G. Slabaugh, and T. Tuytelaars. A continual learning survey: Defying forgetting in classification tasks. IEEE Trans. Pattern Anal. Mach. Intell., 2021. T. DeVries and G. W. Taylor. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552, 2017. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby. An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR, 2021. A. Douillard, Y. Chen, A. Dapogny, and M. Cord. PLOP: Learning without forgetting for continual semantic segmentation. In CVPR, pages 4039–4049, 2021. A. Douillard, M. Cord, C. Ollion, T. Robert, and E. Valle. Podnet: Pooled outputs distillation for smalltasks incremental learning. In ECCV, pages 86–102, 2020. T. Durand, T. Mordan, N. Thome, and M. Cord. Wildcat: Weakly supervised learning of deep convnets for image classification, pointwise localization and segmentation. In CVPR, July 2017. M. Everingham, L. V. Gool, C. K. I. Williams, J. M. Winn, and A. Zisserman. The pascal visual object classes (voc) challenge. IJCV, pages 303–338, 2010. R. Fan, M.M. Cheng, Q. Hou, T.J. Mu, J. Wang, and S.M. Hu. S4net: Single stage salientinstance segmentation. In CVPR, pages 6103–6112, 2019. Y. Gu, C. Deng, and K. Wei. Classincremental instance segmentation via multiteacher networks. In AAAI, pages 1478–1486, 2021. C. Han, J. Lin, J. Mai, Y. Wang, Q. Zhang, B. Zhao, X. Chen, X. Pan, Z. Shi, Z. Xu, S. Yao, L. Yan, H. Lin, X. Huang, C. Liang, G. Han, and Z. Liu. Multilayer pseudosupervision for histopathology tissue semantic segmentation using patchlevel classification labels. Medical Image Analysis, 80:102487, 2022. B. Hariharan, P. Arbeláez, L. Bourdev, S. Maji, and J. Malik. Semantic contours from inverse detectors. In ICCV, pages 991–998, 2011. K. He, H. Fan, Y. Wu, S. Xie, and R. Girshick. Momentum contrast for unsupervised visual representation learning. In CVPR, pages 9729–9738, 2020. K. He, G. Gkioxari, P. Dollar, and R. Girshick. Mask RCNN. In ICCV, pages 2961–2969, 2017. K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In CVPR, pages 770–778, 2016. L. He, Y. Chao, K. Suzuki, and K. Wu. Fast connectedcomponent labeling. PR, pages 1977–1987, 2009. Y.Y. He, P. Zhang, X.S. Wei, X. Zhang, and J. Sun. Relieving longtailed instance segmentation via pairwise class balance. In CVPR, pages 6990–6999, 2022. G. E. Hinton, O. Vinyals, and J. Dean. Distilling the knowledge in a neural network. In NeurIPS Workshop, 2014. S. Hou, X. Pan, C. C. Loy, Z. Wang, and D. Lin. Learning a unified classifier incrementally via rebalancing. In CVPR, pages 831–839, 2019. R. Hu, P. Dollár, K. He, T. Darrell, and R. Girshick. Learning to segment every thing. In CVPR, pages 4233–4241, 2018. Z. Huang, Y. Zou, B. V. K. V. Kumar, and D. Huang. Comprehensive attention selfdistillation for weaklysupervised object detection. In NeurIPS, pages 16797–16807, 2020. C.Y. Hung, C.H. Tu, C.E. Wu, C.H. Chen, Y.M. Chan, and C.S. Chen. Compacting, picking and growing for unforgetting continual learning. In NeurIPS, pages 13647–13657, 2019. J. Hwang, S. Kim, J. Son, and B. Han. Weakly supervised instance segmentation by deep community learning. In WACV, pages 1020–1029, January 2021. A. Iscen, J. Zhang, S. Lazebnik, and C. Schmid. Memoryefficient incremental learning through feature adaptation. In ECCV, pages 699–715. Springer, 2020. L. Jing, Y. Chen, and Y. Tian. Coarsetofine semantic segmentation from imagelevel labels. IEEE Transactions on Image Processing, 29:225–236, 2020. B. Kim, Y. Yoo, C. E. Rhee, and J. Kim. Beyond semantic to instance segmentation: Weaklysupervised instance segmentation via semantic knowledge transfer and selfrefinement. In CVPR, pages 4268–4277, 2022. J. Kirkpatrick, R. Pascanu, N. Rabinowitz, J. Veness, G. Desjardins, A. A. Rusu, K. Milan, J. Quan, T. Ramalho, A. GrabskaBarwinska, et al. Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences, 114(13):3521–3526, 2017. P. Krähenbühl and V. Koltun. Efficient inference in fully connected crfs with gaussian edge potentials. NeurIPS, 24, 2011. H. Kweon, S.H. Yoon, H. Kim, D. Park, and K.J. Yoon. Unlocking the potential of ordinary classifier: Classspecific adversarial erasing framework for weakly supervised semantic segmentation. In ICCV, pages 6994–7003, 2021. J. Lazarow, W. Xu, and Z. Tu. Instance segmentation with masksupervised polygonal boundary transformers. In CVPR, pages 4372–4381, 2022. L. Le Cam. Asymptotic methods in statistical decision theory. Springer Science & Business Media, 2012. Y. Li, Z. Kuang, L. Liu, Y. Chen, and W. Zhang. Pseudomask matters in weaklysupervised semantic segmentation. In ICCV, pages 6944–6953, 2021. Z. Li and D. Hoiem. Learning without forgetting. IEEE TPAMI, 40(12):2935–2947, 2018. T.Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick. Microsoft COCO: Common objects in context. In ECCV, pages 740–755, 2014. Y. Liu, B. Schiele, and Q. Sun. Adaptive aggregation networks for classincremental learning. In CVPR, pages 2544–2553, 2021. Y. Liu, Y. Su, A.A. Liu, B. Schiele, and Q. Sun. Mnemonics training: Multiclass incremental learning without forgetting. In CVPR, June 2020. Y. Liu, Y.H. Wu, P. Wen, Y. Shi, Y. Qiu, and M.M. Cheng. Leveraging instance, image and datasetlevel information for weakly supervised instance segmentation. IEEE TPAMI, 44(3):1415–1428, 2022. Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo. Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV, 2021. M. Lukasik, S. Bhojanapalli, A. Menon, and S. Kumar. Does label smoothing mitigate label noise? In ICML, pages 6448–6458. ICML, 2020. A. Mallya and S. Lazebnik. Packnet: Adding multiple tasks to a single network by iterative pruning. In CVPR, pages 7765–7773, 2018. O. Ostapenko, M. Puscas, T. Klein, P. Jahnichen, and M. Nabi. Learning to remember: A synaptic plasticity driven framework for continual learning. In CVPR, pages 11321–11329, 2019. M. H. Phan, T.A. Ta, S. L. Phung, L. TranThanh, and A. Bouzerdoum. Class similarity weighted knowledge distillation for continual semantic segmentation. In CVPR, pages 16845–16854, 2022. J. PontTuset, P. Arbeláez, J. T. Barron, F. Marques, and J. Malik. Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE TPAMI, 39(1):128–140, 2017. Z. Qian, K. Li, M. Lai, E. I.C. Chang, B. Wei, Y. Fan, and Y. Xu. Transformer based multiple instance learning for weakly supervised histopathology image segmentation. In MICCAI, pages 160–170, 2022. H. Ravishankar, R. Venkataramani, S. Anamandra, P. Sudhakar, and P. Annangi. Feature transformers: privacy preserving lifelong learners for medical imaging. In MICCAI, pages 347–355. Springer, 2019. S.A. Rebuffi, A. Kolesnikov, G. Sperl, and C. H. Lampert. iCaRL: Incremental classifier and representation learning. In CVPR, pages 5533–5542, 2017. Z. Ren, Z. Yu, X. Yang, M.Y. Liu, Y. J. Lee, A. G. Schwing, and J. Kautz. Instanceaware, contextfocused, and memoryefficient weakly supervised object detection. In CVPR, pages 10598–10607, 2020. A. Rosenfeld and J. K. Tsotsos. Incremental learning through deep adaptation. IEEE Trans. Pattern Anal. Mach. Intell., 42(3):651–663, 2018. C. Rother, V. Kolmogorov, and A. Blake. ” grabcut” interactive foreground extraction using iterated graph cuts. ACM TOG, 23(3):309–314, 2004. L. Ru, Y. Zhan, B. Yu, and B. Du. Learning affinity from attention: endtoend weaklysupervised semantic segmentation with transformers. In CVPR, pages 16846–16855, 2022. L. Ru, H. Zheng, Y. Zhan, and B. Du. Token contrast for weaklysupervised semantic segmentation. In CVPR, pages 3093–3102, June 2023. J. Seo, W. Bae, D. J. Sutherland, J. Noh, and D. Kim. Object discovery via contrastive learning for weakly supervised object detection. In ECCV, pages 312–329, 2022. J. Serra, D. Suris, M. Miron, and A. Karatzoglou. Overcoming catastrophic forgetting with hard attention to the task. In ICML, pages 4548–4557. ICML, 2018. H. Shin, J. K. Lee, J. Kim, and J. Kim. Continual learning with deep generative replay. NeurIPS, 30, 2017. K. K. Singh and Y. J. Lee. Hideandseek: Forcing a network to be meticulous for weaklysupervised object and action localization. In ICCV, pages 3544–3553, 2017. R. Strudel, R. Garcia, I. Laptev, and C. Schmid. Segmenter: Transformer for semantic segmentation. In ICCV, pages 7262–7272, 2021. P. Tang, X. Wang, X. Bai, and W. Liu. Multiple instance detection network with online instance classifier refinement. In CVPR, pages 2843–2851, 2017. H. Touvron, M. Cord, M. Douze, F. Massa, A. Sablayrolles, and H. Jegou. Training dataefficient image transformers &; distillation through attention. In ICML, pages 10347–10357. PMLR, 2021. V. K. Verma, K. J. Liang, N. Mehta, P. Rai, and L. Carin. Efficient feature transformations for discriminative and generative continual learning. In CVPR, pages 13865–13875, 2021. T.Y. Wu, G. Swaminathan, Z. Li, A. Ravichandran, N. Vasconcelos, R. Bhotika, and S. Soatto. Classincremental learning with strong pretrained models. In CVPR, pages 9601–9610, June 2022. Z. Wu, C. Shen, and A. van den Hengel. Wider or deeper: Revisiting the resnet model for visual recognition. PR, pages 119–133, 2019. E. Xie, W. Wang, Z. Yu, A. Anandkumar, J. M. Alvarez, and P. Luo. Segformer: Simple and efficient design for semantic segmentation with transformers. In NeurIPS, pages 12077–12090, 2021. S. Yan, J. Xie, and X. He. Der: Dynamically expandable representation for class incremental learning. In CVPR, pages 3014–3023, 2021. J. Yang, C. Li, P. Zhang, X. Dai, B. Xiao, L. Yuan, and J. Gao. Focal attention for longrange interactions in vision transformers. In Advances in Neural Information Processing Systems, pages 30008–30022, 2021. J. Yoon, E. Yang, J. Lee, and S. J. Hwang. Lifelong learning with dynamically expandable networks. arXiv preprint arXiv:1708.01547, 2017. C. Yu, Q. Zhou, J. Li, J. Yuan, Z. Wang, and F. Wang. Foundation model drives weakly incremental learning for semantic segmentation. In CVPR, pages 23685–23694, June 2023. B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba. Learning deep features for discriminative localization. In CVPR, pages 2921–2929, 2016. Y. Zhou, X. Wang, J. Jiao, T. Darrell, and F. Yu. Learning saliency propagation for semisupervised instance segmentation. In CVPR, pages 10307–10316, 2020. Y. Zhou, Y. Zhu, Q. Ye, Q. Qiu, and J. Jiao. Weakly supervised instance segmentation using class peak response. In CVPR, pages 3791–3800, 2018. | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88148 | - |
dc.description.abstract | 以往的實例分割任務需要對圖像中復雜的物體輪廓進行複雜的標註以進行訓練。實際上,標籤也能以逐步的方式提供,以在不同時間步驟中平衡所需的人力資源。然而,目前在實例分割任務上,僅使用弱標籤的增量學習研究仍較沒受到討論。因此在本文中,我們提出了一個持續學習方法,利用圖像級別標籤來分割出物體實例。與大多數依賴傳統方法提供物件候選框的弱監督實例分割不同,我們將弱監督語義分割中的語義知識轉移到弱監督實例分割中生成實例線索。為了解決持續學習中的背景偏移問題,我們利用由過去模型生成的舊類別分割結果來提供更可靠的語義、實例和峰值假設。據我們所知,這是首篇使用圖像標籤的弱監督持續學習實例分割的工作。實驗結果顯示,在不同的增量設置下,我們的方法在Pascal VOC和COCO資料集上都可以達到更好的表現。 | zh_TW |
dc.description.abstract | Instance segmentation in computer vision requires time-consuming manual labeling of complex object contours in images for training. To alleviate the labor-intensive nature of this process, incremental labeling techniques have been explored to distribute human effort across different time steps. However, the field of incremental learning for instance segmentation with weak labels remains underdeveloped. In this study, we propose a novel method for continual learning that enables object instance segmentation using only image-level labels. In contrast to existing weakly-supervised instance segmentation (WSIS) methods that heavily rely on traditional object proposals, we leverage the knowledge gained from weakly-supervised semantic segmentation (WSSS) to generate valuable instance cues. To address the challenge of background shift in continual learning for segmentation, we incorporate the results of previously trained models for old classes. This integration provides more reliable semantic, instance and peak hypotheses during the learning process. To the best of our knowledge, this work is the first to explore weakly-supervised continual learning for instance segmentation in images. Through extensive experiments conducted on the Pascal VOC and COCO datasets, we demonstrate that our proposed method can achieve better performance under various incremental learning settings. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-08-08T16:30:48Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2023-08-08T16:30:48Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | Acknowledgements i
摘要 ii Abstract iii Contents v List of Figures viii List of Tables ix Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Thesis Organization 6 Chapter 2 Related Work 7 2.1 Continual Learning 7 2.1.1 Continual Learning for Semantic Segmentation 9 2.1.2 Continual Learning for Instance Segmentation 11 2.2 Weakly-supervised learning 11 2.2.1 Weakly-supervised Semantic Segmentation 12 2.2.2 Weakly-supervised Object Detection 13 2.2.3 Weakly-supervised Instance Segmentation 14 2.3 Discussion 14 Chapter 3 Methodology 16 3.1 WSSS Preliminary Study 16 3.2 Preliminaries for CL4WSIS 23 3.3 Problem Definition 24 3.4 Overview 24 3.5 CL for WSSS 26 3.5.1 Augmentation Consistency 29 3.5.2 Random Dropout 30 3.6 CL for WSIS 32 3.6.1 Peak Generator (PG) 32 3.6.2 Synthetic Center & Offset Maps Generation 34 3.6.3 Semanticaware Selective Distillation 35 Chapter 4 Experiments 36 4.1 Datasets and Settings 36 4.2 Baselines 38 4.3 Implementation Details 39 4.4 Results 41 4.4.1 Comparison with Pixel-Level Methods 41 4.4.2 Comparison with CL Adapted WSIS Methods 41 4.4.3 COCOtoVOC results 42 4.4.4 Comparison on CL for WSSS 43 4.4.5 Influences of Different Modules 44 4.4.6 Incremental Steps with All Weak Labels Provided 45 4.4.7 Qualitative Analysis 47 Chapter 5 Conclusion 48 References 49 | - |
dc.language.iso | en | - |
dc.title | 基於圖像級標籤的類增量持續學習運用於實例分割 | zh_TW |
dc.title | Image-Level Labels Based Class Incremental Continual Learning for Instance Segmentation | en |
dc.type | Thesis | - |
dc.date.schoolyear | 111-2 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 王鈺強;葉梅珍;楊惠芳 | zh_TW |
dc.contributor.oralexamcommittee | Yu-Chiang Wang;Mei-Chen Yeh;Huei-Fang Yang | en |
dc.subject.keyword | 深度學習,持續學習,弱監督學習,圖像級標籤,實例分割, | zh_TW |
dc.subject.keyword | Deep Learning,Continual Learning,Weakly-Supervised Learning,Image-Level Labels,Instance Segmentation, | en |
dc.relation.page | 59 | - |
dc.identifier.doi | 10.6342/NTU202301024 | - |
dc.rights.note | 同意授權(限校園內公開) | - |
dc.date.accepted | 2023-07-13 | - |
dc.contributor.author-college | 電機資訊學院 | - |
dc.contributor.author-dept | 資訊工程學系 | - |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-111-2.pdf 授權僅限NTU校內IP使用(校園外請利用VPN校外連線服務) | 10.72 MB | Adobe PDF | 檢視/開啟 |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。