references.bib

@ARTICLE{9046805,
  author={Yurtsever, Ekim and Lambert, Jacob and Carballo, Alexander and Takeda, Kazuya},
  journal={IEEE Access}, 
  title={A Survey of Autonomous Driving: Common Practices and Emerging Technologies}, 
  year={2020},
  volume={8},
  number={},
  pages={58443-58469},
  doi={10.1109/ACCESS.2020.2983149}}

@misc{Deichmann_Ebel_Heineke_Heuss_Kellner_Steiner_2023, title={Autonomous Driving’s Future: Convenient and connected}, url={https://www.mckinsey.com/industries/automotive-and-assembly/our-insights/autonomous-drivings-future-convenient-and-connected}, journal={McKinsey & Company}, publisher={McKinsey & Company}, author={Deichmann, Johannes and Ebel, Eike and Heineke, Kersten and Heuss, Ruth and Kellner, Martin and Steiner, Fabian}, year={2023}, month={Jan}} 

@article{doi:10.1080/08839514.2022.2032924,
author = {Irem Ulku and Erdem Akagündüz},
title = {A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D Images},
journal = {Applied Artificial Intelligence},
volume = {36},
number = {1},
pages = {2032924},
year = {2022},
publisher = {Taylor & Francis},
doi = {10.1080/08839514.2022.2032924},
URL = { 
      https://doi.org/10.1080/08839514.2022.2032924
},
eprint = { 
      https://doi.org/10.1080/08839514.2022.2032924
}
}

@inproceedings{Cordts2016Cityscapes,
title={The Cityscapes Dataset for Semantic Urban Scene Understanding},
author={Cordts, Marius and Omran, Mohamed and Ramos, Sebastian and Rehfeld, Timo and Enzweiler, Markus and Benenson, Rodrigo and Franke, Uwe and Roth, Stefan and Schiele, Bernt},
booktitle={Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2016}
}

@misc{Mahna_2021, title={Kitti-road-segmentation}, url={https://www.kaggle.com/datasets/sakshaymahna/kittiroadsegmentation/}, journal={Kaggle}, author={Mahna, Sakshay}, year={2021}, month={Oct}} 

@INPROCEEDINGS{Fritsch2013ITSC,
  author = {Jannik Fritsch and Tobias Kuehnl and Andreas Geiger},
  title = {A New Performance Measure and Evaluation Benchmark for Road Detection Algorithms},
  booktitle = {International Conference on Intelligent Transportation Systems (ITSC)},
  year = {2013}
}

@inproceedings{li-etal-2023-lavis,
    title = "{LAVIS}: A One-stop Library for Language-Vision Intelligence",
    author = "Li, Dongxu  and
      Li, Junnan  and
      Le, Hung  and
      Wang, Guangsen  and
      Savarese, Silvio  and
      Hoi, Steven C.H.",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-demo.3",
    pages = "31--41",
    abstract = "We introduce LAVIS, an open-source deep learning library for LAnguage-VISion research and applications. LAVIS aims to serve as a one-stop comprehensive library that brings recent advancements in the language-vision field accessible for researchers and practitioners, as well as fertilizing future research and development. It features a unified interface to easily access state-of-the-art image-language, video-language models and common datasets. LAVIS supports training, evaluation and benchmarking on a rich variety of tasks, including multimodal classification, retrieval, captioning, visual question answering, dialogue and pre-training. In the meantime, the library is also highly extensible and configurable, facilitating future development and customization. In this technical report, we describe design principles, key components and functionalities of the library, and also present benchmarking results across common language-vision tasks.",
}

@article{DBLP:journals/corr/abs-2201-12086,
  author       = {Junnan Li and
                  Dongxu Li and
                  Caiming Xiong and
                  Steven C. H. Hoi},
  title        = {{BLIP:} Bootstrapping Language-Image Pre-training for Unified Vision-Language
                  Understanding and Generation},
  journal      = {CoRR},
  volume       = {abs/2201.12086},
  year         = {2022},
  url          = {https://arxiv.org/abs/2201.12086},
  eprinttype    = {arXiv},
  eprint       = {2201.12086},
  timestamp    = {Wed, 02 Feb 2022 15:00:01 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2201-12086.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@misc{Rosebrock_2021, title={Image hashing with opencv and python}, url={https://pyimagesearch.com/2017/11/27/image-hashing-opencv-python/}, journal={PyImageSearch}, author={Rosebrock, Adrian}, year={2021}, month={Apr}} 

@InProceedings{10.1007/978-3-319-24574-4_28,
author="Ronneberger, Olaf
and Fischer, Philipp
and Brox, Thomas",
editor="Navab, Nassir
and Hornegger, Joachim
and Wells, William M.
and Frangi, Alejandro F.",
title="U-Net: Convolutional Networks for Biomedical Image Segmentation",
booktitle="Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015",
year="2015",
publisher="Springer International Publishing",
address="Cham",
pages="234--241",
abstract="There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net.",
isbn="978-3-319-24574-4"
}

@INPROCEEDINGS{8305148,
  author={Chaurasia, Abhishek and Culurciello, Eugenio},
  booktitle={2017 IEEE Visual Communications and Image Processing (VCIP)}, 
  title={LinkNet: Exploiting encoder representations for efficient semantic segmentation}, 
  year={2017},
  volume={},
  number={},
  pages={1-4},
  doi={10.1109/VCIP.2017.8305148}}

@INPROCEEDINGS{5206848,
  author={Deng, Jia and Dong, Wei and Socher, Richard and Li, Li-Jia and Kai Li and Li Fei-Fei},
  booktitle={2009 IEEE Conference on Computer Vision and Pattern Recognition}, 
  title={ImageNet: A large-scale hierarchical image database}, 
  year={2009},
  volume={},
  number={},
  pages={248-255},
  doi={10.1109/CVPR.2009.5206848}}

@inproceedings{he2016residual,
  added-at = {2021-05-01T22:31:00.000+0200},
  author = {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  biburl = {https://www.bibsonomy.org/bibtex/2f08d8f1a1881a5c9ee27060e40ada500/nosebrain},
  booktitle = {Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition},
  doi = {10.1109/CVPR.2016.90},
  interhash = {d2fe72bcc2c02bacc9fae990ec4d4927},
  intrahash = {f08d8f1a1881a5c9ee27060e40ada500},
  issn = {1063-6919},
  keywords = {image recognition resnet},
  location = {Las Vegas, NV, USA},
  month = jun,
  pages = {770--778},
  publisher = {IEEE},
  series = {CVPR '16},
  timestamp = {2021-05-01T22:31:00.000+0200},
  title = {{Deep Residual Learning for Image Recognition}},
  url = {http://ieeexplore.ieee.org/document/7780459},
  year = 2016
}

@article{DBLP:journals/corr/SzegedyVISW15,
  author       = {Christian Szegedy and
                  Vincent Vanhoucke and
                  Sergey Ioffe and
                  Jonathon Shlens and
                  Zbigniew Wojna},
  title        = {Rethinking the Inception Architecture for Computer Vision},
  journal      = {CoRR},
  volume       = {abs/1512.00567},
  year         = {2015},
  url          = {http://arxiv.org/abs/1512.00567},
  eprinttype    = {arXiv},
  eprint       = {1512.00567},
  timestamp    = {Mon, 13 Aug 2018 16:49:07 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/SzegedyVISW15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@InProceedings{Simonyan15,
  author       = "Karen Simonyan and Andrew Zisserman",
  title        = "Very Deep Convolutional Networks for Large-Scale Image Recognition",
  booktitle    = "International Conference on Learning Representations",
  year         = "2015",
}

@InProceedings{kingma:adam,
author = {Kingma, Diederick P and Ba, Jimmy},
title = {Adam: A method for stochastic optimization},
booktitle = { International Conference on Learning Representations (ICLR) },
year = {2015}
}

@article{HubermanSpiegelglas2023,
  title      = {An Edit Friendly DDPM Noise Space: Inversion and Manipulations},
  author     = {Huberman-Spiegelglas, Inbar and Kulikov, Vladimir and Michaeli, Tomer},
  journal    = {arXiv preprint arXiv:2304.06140},
  year       = {2023}
}

@misc{tsaban2023ledits,
      title={LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance}, 
      author={Linoy Tsaban and Apolinário Passos},
      year={2023},
      eprint={2307.00522},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@article{Cheng2023,
  title = {A Survey on Image Semantic Segmentation Using Deep Learning Techniques},
  volume = {74},
  ISSN = {1546-2226},
  url = {http://dx.doi.org/10.32604/cmc.2023.032757},
  DOI = {10.32604/cmc.2023.032757},
  number = {1},
  journal = {Computers,  Materials & Continua},
  publisher = {Computers,  Materials and Continua (Tech Science Press)},
  author = {Cheng,  Jieren and Li,  Hua and Li,  Dengbo and Hua,  Shuai and S. Sheng,  Victor},
  year = {2023},
  pages = {1941–1957}
}

@INPROCEEDINGS{9956276,
  author={Lim, Gyeongsup and Kim, Minjae and Hur, Junbeom},
  booktitle={2022 26th International Conference on Pattern Recognition (ICPR)}, 
  title={Adversarial Attack on Semantic Segmentation Preprocessed with Super Resolution}, 
  year={2022},
  volume={},
  number={},
  pages={484-490},
  doi={10.1109/ICPR56361.2022.9956276}}