Deep Multi-Task Learning in Computer Vision


In Defense of the Learning Without Forgetting for Task Incremental Learning
Guy Oren,
Lior Wolf
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Oren_2021_ICCV, author = {Oren, Guy and Wolf, Lior}, title = {In Defense of the Learning Without Forgetting for Task Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {2209-2218} }

UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships Through the Lens of Adversarial Attacks
Naresh Kumar Gurulingan,
Elahe Arani,
Bahram Zonooz
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gurulingan_2021_ICCV, author = {Gurulingan, Naresh Kumar and Arani, Elahe and Zonooz, Bahram}, title = {UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships Through the Lens of Adversarial Attacks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {2239-2248} }

Concurrent Discrimination and Alignment for Self-Supervised Feature Learning
Anjan Dutta,
Massimiliano Mancini,
Zeynep Akata
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dutta_2021_ICCV, author = {Dutta, Anjan and Mancini, Massimiliano and Akata, Zeynep}, title = {Concurrent Discrimination and Alignment for Self-Supervised Feature Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {2189-2198} }

MILA: Multi-Task Learning From Videos via Efficient Inter-Frame Attention
Donghyun Kim,
Tian Lan,
Chuhang Zou,
Ning Xu,
Bryan A. Plummer,
Stan Sclaroff,
Jayan Eledath,
Gerard Medioni
[pdf] [supp]
[bibtex]
@InProceedings{Kim_2021_ICCV, author = {Kim, Donghyun and Lan, Tian and Zou, Chuhang and Xu, Ning and Plummer, Bryan A. and Sclaroff, Stan and Eledath, Jayan and Medioni, Gerard}, title = {MILA: Multi-Task Learning From Videos via Efficient Inter-Frame Attention}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {2219-2229} }

Multi-Modal RGB-D Scene Recognition Across Domains
Andrea Ferreri,
Silvia Bucci,
Tatiana Tommasi
[pdf]
[bibtex]
@InProceedings{Ferreri_2021_ICCV, author = {Ferreri, Andrea and Bucci, Silvia and Tommasi, Tatiana}, title = {Multi-Modal RGB-D Scene Recognition Across Domains}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {2199-2208} }

Audio-Visual Transformer Based Crowd Counting
Usman Sajid,
Xiangyu Chen,
Hasan Sajid,
Taejoon Kim,
Guanghui Wang
[pdf] [arXiv]
[bibtex]
@InProceedings{Sajid_2021_ICCV, author = {Sajid, Usman and Chen, Xiangyu and Sajid, Hasan and Kim, Taejoon and Wang, Guanghui}, title = {Audio-Visual Transformer Based Crowd Counting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {2249-2259} }

ConvNets vs. Transformers: Whose Visual Representations Are More Transferable?
Hong-Yu Zhou,
Chixiang Lu,
Sibei Yang,
Yizhou Yu
[pdf] [arXiv]
[bibtex]
@InProceedings{Zhou_2021_ICCV, author = {Zhou, Hong-Yu and Lu, Chixiang and Yang, Sibei and Yu, Yizhou}, title = {ConvNets vs. Transformers: Whose Visual Representations Are More Transferable?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {2230-2238} }