相关论文: Large Convolutional Model Tuning via Filter Subspa…

Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only tunes a small number of parameters while freezing the vast…

Most of the recent few-shot learning (FSL) algorithms are based on transfer learning, where a model is pre-trained using a large amount of source data, and the pre-trained model is fine-tuned using a small amount of target data. In transfer…

Filters are the essential elements in convolutional neural networks (CNNs). Filters are corresponded to the feature maps and form the main part of the computational and memory requirement for the CNN processing. In filter pruning methods, a…

Recent developments in Parameter-Efficient Fine-Tuning (PEFT) methods for pretrained deep neural networks have captured widespread interest. In this work, we study the enhancement of current PEFT methods by incorporating the spectral…

The advent of high-capacity pre-trained models has revolutionized problem-solving in computer vision, shifting the focus from training task-specific models to adapting pre-trained models. Consequently, effectively adapting large pre-trained…

Popular PEFT methods reduce trainable parameter count for fine-tuning by parameterizing new low-rank or sparse trainable weights in parallel to the frozen pre-trained weights $W$. However, these weights are trained from scratch, and there…

The non-stationary nature of image characteristics calls for adaptive processing, based on the local image content. We propose a simple and flexible method to learn local tuning of parameters in adaptive image processing: we extract simple…

While task-specific finetuning of pretrained networks has led to significant empirical advances in NLP, the large size of networks makes finetuning difficult to deploy in multi-task, memory-constrained settings. We propose diff pruning as a…

Compressing convolutional neural networks (CNNs) is essential for transferring the success of CNNs to a wide variety of applications to mobile devices. In contrast to directly recognizing subtle weights or filters as redundant in a given…

In StyleGAN, convolution kernels are shaped by both static parameters shared across images and dynamic modulation factors $w^+\in\mathcal{W}^+$ specific to each image. Therefore, $\mathcal{W}^+$ space is often used for image inversion and…

A recent family of techniques, dubbed lightweight fine-tuning methods, facilitates parameter-efficient transfer learning by updating only a small set of additional parameters while keeping the parameters of the pretrained language model…

Geometric machine learning models such as graph neural networks have achieved remarkable success in recent years in chemical and materials science research for applications such as high-throughput virtual screening and atomistic…

This paper addresses the issues of parameter redundancy, rigid structure, and limited task adaptability in the fine-tuning of large language models. It proposes an adapter-based fine-tuning method built on a structure-learnable mechanism.…

Parameter-efficient tuning aims to distill knowledge for downstream tasks by optimizing a few introduced parameters while freezing the pretrained language models (PLMs). Continuous prompt tuning which prepends a few trainable vectors to the…

In this paper, we present a semi-supervised fine-tuning approach designed to improve the performance of pre-trained foundation models on downstream tasks with limited labeled data. By leveraging content-style decomposition within an…

Decision-making is a dynamic process requiring perception, memory, and reasoning to make choices and find optimal policies. Traditional approaches to decision-making suffer from sample efficiency and generalization, while large-scale…

Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually…

Convolutional neural networks are based on a huge number of trained weights. Consequently, they are often data-greedy, sensitive to overtraining, and learn slowly. We follow the line of research in which filters of convolutional neural…

The simplest way to obtain continuous interpolation between two points in high dimensional space is to draw a line between them. While previous works focused on the general connectivity between model parameters, we explored linear…

Although pretrained language models can be fine-tuned to produce state-of-the-art results for a very wide range of language understanding tasks, the dynamics of this process are not well understood, especially in the low data regime. Why…