Page: 1... 4 5 6 7 8 9 10 11 12... 282
141 |
GreaseLM: Graph REASoning Enhanced Language Models for Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
142 |
Position-based Prompting for Health Outcome Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
143 |
How to Understand Masked Autoencoders ...
|
|
|
|
Abstract:
"Masked Autoencoders (MAE) Are Scalable Vision Learners" revolutionizes the self-supervised learning method in that it not only achieves the state-of-the-art for image pre-training, but is also a milestone that bridges the gap between visual and linguistic masked autoencoding (BERT-style) pre-trainings. However, to our knowledge, to date there are no theoretical perspectives to explain the powerful expressivity of MAE. In this paper, we, for the first time, propose a unified theoretical framework that provides a mathematical understanding for MAE. Specifically, we explain the patch-based attention approaches of MAE using an integral kernel under a non-overlapping domain decomposition setting. To help the research community to further comprehend the main reasons of the great success of MAE, based on our framework, we pose five questions and answer them with mathematical rigor using insights from operator theory. ...
|
|
Keyword:
Computer Vision and Pattern Recognition cs.CV; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.2202.03670 https://arxiv.org/abs/2202.03670
|
|
BASE
|
|
Hide details
|
|
144 |
Dilated Convolutional Neural Networks for Lightweight Diacritics Restoration ...
|
|
|
|
BASE
|
|
Show details
|
|
145 |
The CLEAR Benchmark: Continual LEArning on Real-World Imagery ...
|
|
|
|
BASE
|
|
Show details
|
|
146 |
Multimodal neural networks better explain multivoxel patterns in the hippocampus ...
|
|
|
|
BASE
|
|
Show details
|
|
147 |
GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records ...
|
|
|
|
BASE
|
|
Show details
|
|
148 |
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations ...
|
|
|
|
BASE
|
|
Show details
|
|
149 |
The Enforcers: Consistent Sparse-Discrete Methods for Constraining Informative Emergent Communication ...
|
|
|
|
BASE
|
|
Show details
|
|
150 |
Who has ears, listen: Citizen Listening Program for disease prevention. ...
|
|
|
|
BASE
|
|
Show details
|
|
151 |
Who has ears, listen: Citizen Listening Program for disease prevention. ...
|
|
|
|
BASE
|
|
Show details
|
|
153 |
Common Phone: A Multilingual Dataset for Robust Acoustic Modelling ...
|
|
|
|
BASE
|
|
Show details
|
|
154 |
Low-dimensional representation of infant and adult vocalization acoustics ...
|
|
|
|
BASE
|
|
Show details
|
|
155 |
Chain-based Discriminative Autoencoders for Speech Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
157 |
Error Correction in ASR using Sequence-to-Sequence Models ...
|
|
|
|
BASE
|
|
Show details
|
|
159 |
Unsupervised word-level prosody tagging for controllable speech synthesis ...
|
|
|
|
BASE
|
|
Show details
|
|
160 |
Filter-based Discriminative Autoencoders for Children Speech Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1... 4 5 6 7 8 9 10 11 12... 282
|
|