Lst: Ladder side-tuning for parameter and memory efficient transfer learning
Fine-tuning large pre-trained models on downstream tasks has been adopted in a variety of
domains recently. However, it is costly to update the entire parameter set of large pre-trained …
domains recently. However, it is costly to update the entire parameter set of large pre-trained …
Mamba-nd: Selective state space modeling for multi-dimensional data
In recent years, Transformers have become the de-facto architecture for sequence modeling
on text and multi-dimensional data, such as images and video. However, the use of self …
on text and multi-dimensional data, such as images and video. However, the use of self …
Unipt: Universal parallel tuning for transfer learning with efficient parameter and memory
Parameter-efficient transfer learning (PETL) ie fine-tuning a small portion of parameters is an
effective strategy for adapting pre-trained models to downstream domains. To further reduce …
effective strategy for adapting pre-trained models to downstream domains. To further reduce …
Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
As artificial intelligence systems grow more powerful, there has been increasing interest in"
AI safety" research to address emerging and future risks. However, the field of AI safety …
AI safety" research to address emerging and future risks. However, the field of AI safety …
Marsformer: Martian rock semantic segmentation with transformer
Semantic segmentation of Mars scenes has a crucial role in Mars rovers science missions.
Current convolutional neural network (CNN)-based composition of U-Net has powerful …
Current convolutional neural network (CNN)-based composition of U-Net has powerful …
Re2TAL: Rewiring pretrained video backbones for reversible temporal action localization
Temporal action localization (TAL) requires long-form reasoning to predict actions of various
durations and complex content. Given limited GPU memory, training TAL end to end (ie, from …
durations and complex content. Given limited GPU memory, training TAL end to end (ie, from …
MMIF-INet: Multimodal medical image fusion by invertible network
Multimodal medical image fusion (MMIF) technology aims to generate fused images that
comprehensively reflect the information of tissues, organs, and metabolism, thereby …
comprehensively reflect the information of tissues, organs, and metabolism, thereby …
Invertible diffusion models for compressed sensing
While deep neural networks (NN) significantly advance image compressed sensing (CS) by
improving reconstruction quality, the necessity of training current CS NNs from scratch …
improving reconstruction quality, the necessity of training current CS NNs from scratch …
Sherl: Synthesizing high accuracy and efficient memory for resource-limited transfer learning
Parameter-efficient transfer learning (PETL) has emerged as a flourishing research field for
adapting large pre-trained models to downstream tasks, greatly reducing trainable …
adapting large pre-trained models to downstream tasks, greatly reducing trainable …
Efficient pneumonia detection using Vision Transformers on chest X-rays
Pneumonia is a widespread and acute respiratory infection that impacts people of all ages.
Early detection and treatment of pneumonia are essential for avoiding complications and …
Early detection and treatment of pneumonia are essential for avoiding complications and …