CVPR 2024 Open Access Repository

The 7th Workshop on Efficient Deep Learning for Computer Vision (ECV24)

Masked Autoencoders are Secretly Efficient Learners: Zihao Wei,

Chen Wei,

Jieru Mei,

Yutong Bai,

Zeyu Wang,

Xianhang Li,

Hongru Zhu,

Huiyu Wang,

Alan Yuille,

Yuyin Zhou,

Cihang Xie; [pdf]
[bibtex]
@InProceedings{Wei_2024_CVPR, author = {Wei, Zihao and Wei, Chen and Mei, Jieru and Bai, Yutong and Wang, Zeyu and Li, Xianhang and Zhu, Hongru and Wang, Huiyu and Yuille, Alan and Zhou, Yuyin and Xie, Cihang}, title = {Masked Autoencoders are Secretly Efficient Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {7986-7995} }
Data-Efficient and Robust Task Selection for Meta-Learning: Donglin Zhan,

James Anderson; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhan_2024_CVPR, author = {Zhan, Donglin and Anderson, James}, title = {Data-Efficient and Robust Task Selection for Meta-Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8056-8065} }
FlowIBR: Leveraging Pre-Training for Efficient Neural Image-Based Rendering of Dynamic Scenes: Marcel Büsching,

Josef Bengtson,

David Nilsson,

Mårten Björkman; [pdf] [supp]
[bibtex]
@InProceedings{Busching_2024_CVPR, author = {B\"usching, Marcel and Bengtson, Josef and Nilsson, David and Bj\"orkman, M\r{a}rten}, title = {FlowIBR: Leveraging Pre-Training for Efficient Neural Image-Based Rendering of Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8016-8026} }
Multi-Objective Hardware Aware Neural Architecture Search using Hardware Cost Diversity: Nilotpal Sinha,

Peyman Rostami,

Abd El Rahman Shabayek,

Anis Kacem,

Djamila Aouada; [pdf] [arXiv]
[bibtex]
@InProceedings{Sinha_2024_CVPR, author = {Sinha, Nilotpal and Rostami, Peyman and El Rahman Shabayek, Abd and Kacem, Anis and Aouada, Djamila}, title = {Multi-Objective Hardware Aware Neural Architecture Search using Hardware Cost Diversity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8032-8039} }
ShiftAddAug: Augment Multiplication-Free Tiny Neural Network with Hybrid Computation: Yipin Guo,

Zihao Li,

Yilin Lang,

Qinyuan Ren; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2024_CVPR, author = {Guo, Yipin and Li, Zihao and Lang, Yilin and Ren, Qinyuan}, title = {ShiftAddAug: Augment Multiplication-Free Tiny Neural Network with Hybrid Computation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8075-8084} }
Block Selective Reprogramming for On-device Training of Vision Transformers: Sreetama Sarkar,

Souvik Kundu,

Kai Zheng,

Peter A. Beerel; [pdf] [arXiv]
[bibtex]
@InProceedings{Sarkar_2024_CVPR, author = {Sarkar, Sreetama and Kundu, Souvik and Zheng, Kai and Beerel, Peter A.}, title = {Block Selective Reprogramming for On-device Training of Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8094-8103} }
ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration: Ning-Chi Huang,

Chi-Chih Chang,

Wei-Cheng Lin,

Endri Taka,

Diana Marculescu,

Kai-Chiang Wu; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, Ning-Chi and Chang, Chi-Chih and Lin, Wei-Cheng and Taka, Endri and Marculescu, Diana and Wu, Kai-Chiang}, title = {ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8006-8015} }
SuperLoRA: Parameter-Efficient Unified Adaptation for Large Vision Models: Xiangyu Chen,

Jing Liu,

Ye Wang,

Pu Wang,

Matthew Brand,

Guanghui Wang,

Toshiaki Koike-Akino; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Xiangyu and Liu, Jing and Wang, Ye and Wang, Pu and Brand, Matthew and Wang, Guanghui and Koike-Akino, Toshiaki}, title = {SuperLoRA: Parameter-Efficient Unified Adaptation for Large Vision Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8050-8055} }
Cache and Reuse: Rethinking the Efficiency of On-device Transfer Learning: Yuedong Yang,

Hung-Yueh Chiang,

Guihong Li,

Diana Marculescu,

Radu Marculescu; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2024_CVPR, author = {Yang, Yuedong and Chiang, Hung-Yueh and Li, Guihong and Marculescu, Diana and Marculescu, Radu}, title = {Cache and Reuse: Rethinking the Efficiency of On-device Transfer Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8040-8049} }
Improving the Efficiency-Accuracy Trade-off of DETR-Style Models in Practice: Yumin Suh,

Dongwan Kim,

Abhishek Aich,

Samuel Schulter,

Jong-Chyi Su,

Bohyung Han,

Manmohan Chandraker; [pdf]
[bibtex]
@InProceedings{Suh_2024_CVPR, author = {Suh, Yumin and Kim, Dongwan and Aich, Abhishek and Schulter, Samuel and Su, Jong-Chyi and Han, Bohyung and Chandraker, Manmohan}, title = {Improving the Efficiency-Accuracy Trade-off of DETR-Style Models in Practice}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8027-8031} }
MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers: Tanvir Mahmud,

Shentong Mo,

Yapeng Tian,

Diana Marculescu; [pdf] [supp]
[bibtex]
@InProceedings{Mahmud_2024_CVPR, author = {Mahmud, Tanvir and Mo, Shentong and Tian, Yapeng and Marculescu, Diana}, title = {MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {7996-8005} }
Selectively Dilated Convolution for Accuracy-Preserving Sparse Pillar-based Embedded 3D Object Detection: Seongmin Park,

Minjae Lee,

Junwon Choi,

Jungwook Choi; [pdf] [arXiv]
[bibtex]
@InProceedings{Park_2024_CVPR, author = {Park, Seongmin and Lee, Minjae and Choi, Junwon and Choi, Jungwook}, title = {Selectively Dilated Convolution for Accuracy-Preserving Sparse Pillar-based Embedded 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8104-8113} }
The Revenge of BiSeNet: Efficient Multi-Task Image Segmentation: Gabriele Rosi,

Claudia Cuttano,

Niccolò Cavagnero,

Giuseppe Averta,

Fabio Cermelli; [pdf] [arXiv]
[bibtex]
@InProceedings{Rosi_2024_CVPR, author = {Rosi, Gabriele and Cuttano, Claudia and Cavagnero, Niccol\`o and Averta, Giuseppe and Cermelli, Fabio}, title = {The Revenge of BiSeNet: Efficient Multi-Task Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8066-8074} }
LVS: A Learned Video Storage for Fast and Efficient Video Understanding: Yunghee Lee,

Jongse Park; [pdf]
[bibtex]
@InProceedings{Lee_2024_CVPR, author = {Lee, Yunghee and Park, Jongse}, title = {LVS: A Learned Video Storage for Fast and Efficient Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8085-8093} }