no code implementations • 9 Nov 2023 • Daniel Bolya, Chaitanya Ryali, Judy Hoffman, Christoph Feichtenhofer
To fix it, we introduce a simple absolute window position embedding strategy, which solves the bug outright in Hiera and allows us to increase both speed and performance of the model in ViTDet.
2 code implementations • 1 Jun 2023 • 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
Modern hierarchical vision transformers have added several vision-specific components in the pursuit of supervised classification performance.
Ranked #1 on Image Classification on iNaturalist 2019 (using extra training data)
1 code implementation • 4 May 2023 • George Stoica, Daniel Bolya, Jakob Bjorner, Pratik Ramesh, Taylor Hearn, Judy Hoffman
While this works for models trained on the same task, we find that this fails to account for the differences in models trained on disjoint tasks.
3 code implementations • 30 Mar 2023 • Daniel Bolya, Judy Hoffman
In the process, we speed up image generation by up to 2x and reduce memory consumption by up to 5. 6x.
3 code implementations • 17 Oct 2022 • Daniel Bolya, Cheng-Yang Fu, Xiaoliang Dai, Peizhao Zhang, Christoph Feichtenhofer, Judy Hoffman
Off-the-shelf, ToMe can 2x the throughput of state-of-the-art ViT-L @ 512 and ViT-H @ 518 models on images and 2. 2x the throughput of ViT-L on video with only a 0. 2-0. 3% accuracy drop in each case.
Ranked #13 on Efficient ViTs on ImageNet-1K (with DeiT-S)
no code implementations • 15 Sep 2022 • Daniel Bolya, Cheng-Yang Fu, Xiaoliang Dai, Peizhao Zhang, Judy Hoffman
While transformers have begun to dominate many tasks in vision, applying them to large images is still computationally difficult.
1 code implementation • NeurIPS 2021 • Daniel Bolya, Rohit Mittapalli, Judy Hoffman
In this paper, we formalize this setting as "Scalable Diverse Model Selection" and propose several benchmarks for evaluating on this task.
no code implementations • 25 Aug 2020 • Fu Lin, Rohit Mittapalli, Prithvijit Chattopadhyay, Daniel Bolya, Judy Hoffman
Convolutional Neural Networks have been shown to be vulnerable to adversarial examples, which are known to locate in subspaces close to where normal data lies but are not naturally occurring and of low probability.
2 code implementations • ECCV 2020 • Daniel Bolya, Sean Foley, James Hays, Judy Hoffman
We introduce TIDE, a framework and associated toolbox for analyzing the sources of error in object detection and instance segmentation algorithms.
36 code implementations • 3 Dec 2019 • Daniel Bolya, Chong Zhou, Fanyi Xiao, Yong Jae Lee
Then we produce instance masks by linearly combining the prototypes with the mask coefficients.
Ranked #15 on Real-time Instance Segmentation on MSCOCO (using extra training data)
48 code implementations • ICCV 2019 • Daniel Bolya, Chong Zhou, Fanyi Xiao, Yong Jae Lee
Then we produce instance masks by linearly combining the prototypes with the mask coefficients.
Ranked #21 on Real-time Instance Segmentation on MSCOCO (using extra training data)