D2
Computer Vision and Machine Learning

Di Chen

Personal Information

Publications

Böhle, M., Fritz, M., & Schiele, B. (2022). B-cos Networks: Alignment is All We Need for Interpretability. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022). New Orleans, LA, USA: IEEE. doi:10.1109/CVPR52688.2022.01008
Export
BibTeX
@inproceedings{Boehle_CVPR2022, TITLE = {B-cos Networks: {A}lignment is All We Need for Interpretability}, AUTHOR = {B{\"o}hle, Moritz and Fritz, Mario and Schiele, Bernt}, LANGUAGE = {eng}, ISBN = {978-1-6654-6946-3}, DOI = {10.1109/CVPR52688.2022.01008}, PUBLISHER = {IEEE}, YEAR = {2022}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)}, PAGES = {10319--10328}, ADDRESS = {New Orleans, LA, USA}, }
Endnote
%0 Conference Proceedings %A Böhle, Moritz %A Fritz, Mario %A Schiele, Bernt %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T B-cos Networks: Alignment is All We Need for Interpretability : %G eng %U http://hdl.handle.net/21.11116/0000-000A-6F96-1 %R 10.1109/CVPR52688.2022.01008 %D 2022 %B 35th IEEE/CVF Conference on Computer Vision and Pattern Recognition %Z date of event: 2022-06-19 - 2022-06-24 %C New Orleans, LA, USA %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 10319 - 10328 %I IEEE %@ 978-1-6654-6946-3
Rao, S., Böhle, M., & Schiele, B. (2022). Towards Better Understanding Attribution Methods. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022). New Orleans, LA, USA: IEEE. doi:10.1109/CVPR52688.2022.00998
Export
BibTeX
@inproceedings{Rao_CVPR2022, TITLE = {Towards Better Understanding Attribution Methods}, AUTHOR = {Rao, Sukrut and B{\"o}hle, Moritz and Schiele, Bernt}, LANGUAGE = {eng}, ISBN = {978-1-6654-6946-3}, DOI = {10.1109/CVPR52688.2022.00998}, PUBLISHER = {IEEE}, YEAR = {2022}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)}, PAGES = {10213--10222}, ADDRESS = {New Orleans, LA, USA}, }
Endnote
%0 Conference Proceedings %A Rao, Sukrut %A Böhle, Moritz %A Schiele, Bernt %+ Computer Graphics, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Towards Better Understanding Attribution Methods : %G eng %U http://hdl.handle.net/21.11116/0000-000A-6F91-6 %R 10.1109/CVPR52688.2022.00998 %D 2022 %B 35th IEEE/CVF Conference on Computer Vision and Pattern Recognition %Z date of event: 2022-06-19 - 2022-06-24 %C New Orleans, LA, USA %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 10213 - 10222 %I IEEE %@ 978-1-6654-6946-3
Böhle, M. D., Fritz, M., & Schiele, B. (2021a). Convolutional Dynamic Alignment Networks for Interpretable Classifications. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021). Nashville, TN, USA (Virtual): IEEE. doi:10.1109/CVPR46437.2021.00990
Export
BibTeX
@inproceedings{Boehle_CVPR21, TITLE = {Convolutional Dynamic Alignment Networks for Interpretable Classifications}, AUTHOR = {B{\"o}hle, Moritz Daniel and Fritz, Mario and Schiele, Bernt}, LANGUAGE = {eng}, ISBN = {978-1-6654-4509-2}, DOI = {10.1109/CVPR46437.2021.00990}, PUBLISHER = {IEEE}, YEAR = {2021}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021)}, PAGES = {10029--10038}, ADDRESS = {Nashville, TN, USA (Virtual)}, }
Endnote
%0 Conference Proceedings %A Böhle, Moritz Daniel %A Fritz, Mario %A Schiele, Bernt %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Convolutional Dynamic Alignment Networks for Interpretable Classifications : %G eng %U http://hdl.handle.net/21.11116/0000-0008-1863-E %R 10.1109/CVPR46437.2021.00990 %D 2021 %B 34th IEEE Conference on Computer Vision and Pattern Recognition %Z date of event: 2021-06-19 - 2021-06-25 %C Nashville, TN, USA (Virtual) %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 10029 - 10038 %I IEEE %@ 978-1-6654-4509-2
Böhle, M. D., Fritz, M., & Schiele, B. (2021b). Optimising for Interpretability: Convolutional Dynamic Alignment Networks. Retrieved from https://arxiv.org/abs/2109.13004
(arXiv: 2109.13004)
Abstract
We introduce a new family of neural network models called Convolutional<br>Dynamic Alignment Networks (CoDA Nets), which are performant classifiers with a<br>high degree of inherent interpretability. Their core building blocks are<br>Dynamic Alignment Units (DAUs), which are optimised to transform their inputs<br>with dynamically computed weight vectors that align with task-relevant<br>patterns. As a result, CoDA Nets model the classification prediction through a<br>series of input-dependent linear transformations, allowing for linear<br>decomposition of the output into individual input contributions. Given the<br>alignment of the DAUs, the resulting contribution maps align with<br>discriminative input patterns. These model-inherent decompositions are of high<br>visual quality and outperform existing attribution methods under quantitative<br>metrics. Further, CoDA Nets constitute performant classifiers, achieving on par<br>results to ResNet and VGG models on e.g. CIFAR-10 and TinyImagenet. Lastly,<br>CoDA Nets can be combined with conventional neural network models to yield<br>powerful classifiers that more easily scale to complex datasets such as<br>Imagenet whilst exhibiting an increased interpretable depth, i.e., the output<br>can be explained well in terms of contributions from intermediate layers within<br>the network.<br>
Export
BibTeX
@online{Boehle2109.13004, TITLE = {Optimising for Interpretability: Convolutional Dynamic Alignment Networks}, AUTHOR = {B{\"o}hle, Moritz Daniel and Fritz, Mario and Schiele, Bernt}, LANGUAGE = {eng}, URL = {https://arxiv.org/abs/2109.13004}, EPRINT = {2109.13004}, EPRINTTYPE = {arXiv}, YEAR = {2021}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We introduce a new family of neural network models called Convolutional<br>Dynamic Alignment Networks (CoDA Nets), which are performant classifiers with a<br>high degree of inherent interpretability. Their core building blocks are<br>Dynamic Alignment Units (DAUs), which are optimised to transform their inputs<br>with dynamically computed weight vectors that align with task-relevant<br>patterns. As a result, CoDA Nets model the classification prediction through a<br>series of input-dependent linear transformations, allowing for linear<br>decomposition of the output into individual input contributions. Given the<br>alignment of the DAUs, the resulting contribution maps align with<br>discriminative input patterns. These model-inherent decompositions are of high<br>visual quality and outperform existing attribution methods under quantitative<br>metrics. Further, CoDA Nets constitute performant classifiers, achieving on par<br>results to ResNet and VGG models on e.g. CIFAR-10 and TinyImagenet. Lastly,<br>CoDA Nets can be combined with conventional neural network models to yield<br>powerful classifiers that more easily scale to complex datasets such as<br>Imagenet whilst exhibiting an increased interpretable depth, i.e., the output<br>can be explained well in terms of contributions from intermediate layers within<br>the network.<br>}, }
Endnote
%0 Report %A B&#246;hle, Moritz Daniel %A Fritz, Mario %A Schiele, Bernt %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Optimising for Interpretability: Convolutional Dynamic Alignment Networks : %G eng %U http://hdl.handle.net/21.11116/0000-0009-8113-F %U https://arxiv.org/abs/2109.13004 %D 2021 %X We introduce a new family of neural network models called Convolutional<br>Dynamic Alignment Networks (CoDA Nets), which are performant classifiers with a<br>high degree of inherent interpretability. Their core building blocks are<br>Dynamic Alignment Units (DAUs), which are optimised to transform their inputs<br>with dynamically computed weight vectors that align with task-relevant<br>patterns. As a result, CoDA Nets model the classification prediction through a<br>series of input-dependent linear transformations, allowing for linear<br>decomposition of the output into individual input contributions. Given the<br>alignment of the DAUs, the resulting contribution maps align with<br>discriminative input patterns. These model-inherent decompositions are of high<br>visual quality and outperform existing attribution methods under quantitative<br>metrics. Further, CoDA Nets constitute performant classifiers, achieving on par<br>results to ResNet and VGG models on e.g. CIFAR-10 and TinyImagenet. Lastly,<br>CoDA Nets can be combined with conventional neural network models to yield<br>powerful classifiers that more easily scale to complex datasets such as<br>Imagenet whilst exhibiting an increased interpretable depth, i.e., the output<br>can be explained well in terms of contributions from intermediate layers within<br>the network.<br> %K Statistics, Machine Learning, stat.ML,Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Learning, cs.LG