Masked modeling for self-supervised representation learning on vision and beyond

S Li, L Zhang, Z Wang, D Wu, L Wu, Z Liu, J Xia… - arXiv preprint arXiv …, 2023 - arxiv.org
As the deep learning revolution marches on, self-supervised learning has garnered
increasing attention in recent years thanks to its remarkable representation learning ability …

Semantic-DARTS: Elevating Semantic Learning for Mobile Differentiable Architecture Search

B Guo, S He, M Shi, K Yu, J Chen… - IEEE Internet of Things …, 2024 - ieeexplore.ieee.org
Differentiable ARchitecture Search (DARTS) is a prevailing direction in automatic machine
learning, but it may suffer from performance collapse and generalization issues. Recent …

Understanding Sentiment Polarities and Emotion Categories of People on Public Incidents With the Relation to Government Policies

H Zou, Y Wang - IEEE Transactions on Computational Social …, 2024 - ieeexplore.ieee.org
Public incidents necessitate prompt proactive measures by the government and pertinent
departments, posing substantial challenges to emergency management capabilities. With …

Local Masking Meets Progressive Freezing: Crafting Efficient Vision Transformers for Self-Supervised Learning

UM Topcuoglu, E Akagündüz - arXiv preprint arXiv:2312.02194, 2023 - arxiv.org
In this paper, we present an innovative approach to self-supervised learning for Vision
Transformers (ViTs), integrating local masked image modeling with progressive layer …

StyleInject: Parameter Efficient Tuning of Text-to-Image Diffusion Models

M Zhou, Y Bai, Q Yang, T Zhao - arXiv preprint arXiv:2401.13942, 2024 - arxiv.org
The ability to fine-tune generative models for text-to-image generation tasks is crucial,
particularly facing the complexity involved in accurately interpreting and visualizing textual …

NR-MAE: noise reduction masked autoencoder for boosting SSL on SAR target recognition

X Chen, W Li, Y Liu, Z Liu, T Liu… - Conference on …, 2024 - spiedigitallibrary.org
Self-supervised learning models can effectively adapt to the prevailing big data trend,
leading to their extensive applications in various domains. Nevertheless, image degradation …