Daniel Bolya

According to our database, Daniel Bolya authored at least 13 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Less is More: Accelerating Vision by Eliminating Redundancy.

Daniel Bolya

PhD thesis, 2024

ZipIt! Merging Models from Different Tasks without Training.

George Stoica, Daniel Bolya, Jakob Bjorner, Pratik Ramesh, Taylor Hearn, Judy Hoffman

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Window Attention is Bugged: How not to Interpolate Position Embeddings.

Daniel Bolya, Chaitanya Ryali, Judy Hoffman, Christoph Feichtenhofer

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

ZipIt! Merging Models from Different Tasks without Training.

George Stoica, Daniel Bolya, Jakob Bjorner, Taylor Hearn, Judy Hoffman

CoRR, 2023

Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles.

Chaitanya Ryali, Yuan-Ting Hu, Daniel Bolya, Chen Wei, Haoqi Fan, Po-Yao Huang, Vaibhav Aggarwal, Arkabandhu Chowdhury, Omid Poursaeed, Judy Hoffman, Jitendra Malik, Yanghao Li, Christoph Feichtenhofer

Proceedings of the International Conference on Machine Learning, 2023

Token Merging: Your ViT But Faster.

Daniel Bolya, Cheng-Yang Fu, Xiaoliang Dai, Peizhao Zhang, Christoph Feichtenhofer, Judy Hoffman

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Token Merging for Fast Stable Diffusion.

Daniel Bolya, Judy Hoffman

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

YOLACT++ Better Real-Time Instance Segmentation.

Daniel Bolya, Chong Zhou, Fanyi Xiao, Yong Jae Lee

IEEE Trans. Pattern Anal. Mach. Intell., 2022

Hydra Attention: Efficient Attention with Many Heads.

Daniel Bolya, Cheng-Yang Fu, Xiaoliang Dai, Peizhao Zhang, Judy Hoffman

Proceedings of the Computer Vision - ECCV 2022 Workshops, 2022

2021

Scalable Diverse Model Selection for Accessible Transfer Learning.

Daniel Bolya, Rohit Mittapalli, Judy Hoffman

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Likelihood Landscapes: A Unifying Principle Behind Many Adversarial Defenses.

Fu Lin, Rohit Mittapalli, Prithvijit Chattopadhyay, Daniel Bolya, Judy Hoffman

Proceedings of the Computer Vision - ECCV 2020 Workshops, 2020

TIDE: A General Toolbox for Identifying Object Detection Errors.

Daniel Bolya, Sean Foley, James Hays, Judy Hoffman

Proceedings of the Computer Vision - ECCV 2020, 2020

2019

YOLACT: Real-Time Instance Segmentation.

Daniel Bolya, Chong Zhou, Fanyi Xiao, Yong Jae Lee

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019