Efficient and Versatile Robust Fine-Tuning of Zero-shot Models
- URL: http://arxiv.org/abs/2408.05749v1
- Date: Sun, 11 Aug 2024 11:37:43 GMT
- Title: Efficient and Versatile Robust Fine-Tuning of Zero-shot Models
- Authors: Sungyeon Kim, Boseung Jeong, Donghyun Kim, Suha Kwak,
- Abstract summary: We introduce Robust Adapter (R-Adapter), a novel method for fine-tuning zero-shot models to downstream tasks.
Our method integrates lightweight modules into the pre-trained model and employs novel self-ensemble techniques to boost OOD robustness and reduce storage expenses substantially.
Our experiments demonstrate that R-Adapter achieves state-of-the-art performance across a diverse set of tasks, tuning only 13% of the parameters of the CLIP encoders.
- Score: 34.27380518351181
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which reduces generalization to out-of-distribution (OOD) data and demands extensive computational resources. We introduce Robust Adapter (R-Adapter), a novel method for fine-tuning zero-shot models to downstream tasks while simultaneously addressing both these issues. Our method integrates lightweight modules into the pre-trained model and employs novel self-ensemble techniques to boost OOD robustness and reduce storage expenses substantially. Furthermore, we propose MPM-NCE loss designed for fine-tuning on vision-language downstream tasks. It ensures precise alignment of multiple image-text pairs and discriminative feature learning. By extending the benchmark for robust fine-tuning beyond classification to include diverse tasks such as cross-modal retrieval and open vocabulary segmentation, we demonstrate the broad applicability of R-Adapter. Our extensive experiments demonstrate that R-Adapter achieves state-of-the-art performance across a diverse set of tasks, tuning only 13% of the parameters of the CLIP encoders.
Related papers
- Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting [107.4034346788744]
Existing vehicle trajectory prediction models struggle with generalizability, prediction uncertainties, and handling complex interactions.
We propose Perceiver with Register queries (PerReg+), a novel trajectory prediction framework that introduces: (1) Dual-Level Representation Learning via Self-Distillation (SD) and Masked Reconstruction (MR), capturing global context and fine-grained details; (2) Enhanced Multimodality using register-based queries and pretraining, eliminating the need for clustering and suppression; and (3) Adaptive Prompt Tuning during fine-tuning, freezing the main architecture and optimizing a small number of prompts for efficient adaptation.
arXiv Detail & Related papers (2025-01-08T20:11:09Z) - FineGates: LLMs Finetuning with Compression using Stochastic Gates [7.093692674858257]
Large Language Models (LLMs) present significant challenges for full finetuning due to the high computational demands.
Lightweight finetuning techniques have been proposed, like learning low-rank adapter layers.
We propose an adaptor model based on gates that simultaneously sparsify the frozen base model with task-specific adaptation.
arXiv Detail & Related papers (2024-12-17T14:33:05Z) - Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities.
In-Context Learning (ICL) and.
Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting.
LLMs to downstream tasks.
We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
arXiv Detail & Related papers (2024-09-30T10:48:20Z) - Adversarial Robustification via Text-to-Image Diffusion Models [56.37291240867549]
Adrial robustness has been conventionally believed as a challenging property to encode for neural networks.
We develop a scalable and model-agnostic solution to achieve adversarial robustness without using any data.
arXiv Detail & Related papers (2024-07-26T10:49:14Z) - Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization.
A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR.
For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
arXiv Detail & Related papers (2024-07-11T10:35:53Z) - AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning [22.950914612765494]
Fine-tuning large language models (LLMs) has achieved remarkable performance across various natural language processing tasks.
Memory-efficient Zeroth-order (MeZO) methods attempt to fine-tune LLMs using only forward passes, thereby avoiding the need for a backpropagation graph.
We propose the Adaptive Zeroth-order-Train Adaption (AdaZeta) framework, specifically designed to improve the performance and convergence of the ZO methods.
arXiv Detail & Related papers (2024-06-26T04:33:13Z) - E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation [69.72194342962615]
We introduce and address a novel research direction: can the process of distilling GANs from diffusion models be made significantly more efficient?
First, we construct a base GAN model with generalized features, adaptable to different concepts through fine-tuning, eliminating the need for training from scratch.
Second, we identify crucial layers within the base GAN model and employ Low-Rank Adaptation (LoRA) with a simple yet effective rank search process, rather than fine-tuning the entire base model.
Third, we investigate the minimal amount of data necessary for fine-tuning, further reducing the overall training time.
arXiv Detail & Related papers (2024-01-11T18:59:14Z) - Parameter-Efficient Transfer Learning for Remote Sensing Image-Text
Retrieval [10.84733740863356]
In this work, we investigate the parameter-efficient transfer learning (PETL) method to transfer visual-language knowledge from the natural domain to the RS domain on the image-text retrieval task.
Our proposed model only contains 0.16M training parameters, which can achieve a parameter reduction of 98.9% compared to full fine-tuning.
Our retrieval performance exceeds traditional methods by 7-13% and achieves comparable or better performance than full fine-tuning.
arXiv Detail & Related papers (2023-08-24T02:43:53Z) - Precision-Recall Divergence Optimization for Generative Modeling with
GANs and Normalizing Flows [54.050498411883495]
We develop a novel training method for generative models, such as Generative Adversarial Networks and Normalizing Flows.
We show that achieving a specified precision-recall trade-off corresponds to minimizing a unique $f$-divergence from a family we call the textitPR-divergences.
Our approach improves the performance of existing state-of-the-art models like BigGAN in terms of either precision or recall when tested on datasets such as ImageNet.
arXiv Detail & Related papers (2023-05-30T10:07:17Z) - Surrogate Lagrangian Relaxation: A Path To Retrain-free Deep Neural
Network Pruning [9.33753001494221]
Network pruning is a widely used technique to reduce computation cost and model size for deep neural networks.
In this paper, we develop a systematic weight-pruning optimization approach based on Surrogate Lagrangian relaxation.
arXiv Detail & Related papers (2023-04-08T22:48:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.