Directional Gradient Projection for Robust Fine-Tuning of Foundation Models

• URL: http://arxiv.org/abs/2502.15895v1
• Date: Fri, 21 Feb 2025 19:31:55 GMT
• Title: Directional Gradient Projection for Robust Fine-Tuning of Foundation Models
• Authors: Chengyue Huang, Junjiao Tian, Brisa Maneechotesuwan, Shivang Chopra, Zsolt Kira,
• Abstract summary: Directional Gradient Projection (DiGraP) is a layer-wise trainable method that incorporates directional information from gradients to bridge regularization and multi-objective optimization.<n>We first bridge the uni-modal and multi-modal gap by performing analysis on Image Classification reformulated Visual Question Answering (VQA) benchmarks.<n> Experimental results show that DiGraP consistently outperforms existing baselines across Image Classfication and VQA tasks with discriminative and generative backbones.
• Score: 25.04763038570959
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Robust fine-tuning aims to adapt large foundation models to downstream tasks while preserving their robustness to distribution shifts. Existing methods primarily focus on constraining and projecting current model towards the pre-trained initialization based on the magnitudes between fine-tuned and pre-trained weights, which often require extensive hyper-parameter tuning and can sometimes result in underfitting. In this work, we propose Directional Gradient Projection (DiGraP), a novel layer-wise trainable method that incorporates directional information from gradients to bridge regularization and multi-objective optimization. Besides demonstrating our method on image classification, as another contribution we generalize this area to the multi-modal evaluation settings for robust fine-tuning. Specifically, we first bridge the uni-modal and multi-modal gap by performing analysis on Image Classification reformulated Visual Question Answering (VQA) benchmarks and further categorize ten out-of-distribution (OOD) VQA datasets by distribution shift types and degree (i.e. near versus far OOD). Experimental results show that DiGraP consistently outperforms existing baselines across Image Classfication and VQA tasks with discriminative and generative backbones, improving both in-distribution (ID) generalization and OOD robustness.

Related papers

• Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations [2.992602379681373]
  We show that multi-modal fine-tuning can achieve notable OoDD performance. We propose a training objective that enhances cross-modal alignment by regularizing the distances between image and text embeddings of ID data.
  arXiv  Detail & Related papers  (2025-03-24T16:00:21Z)
• Semi-Supervised Fine-Tuning of Vision Foundation Models with Content-Style Decomposition [4.192370959537781]
  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. We evaluate our approach on multiple datasets, including MNIST, its augmented variations, CIFAR-10, SVHN, and GalaxyMNIST.
  arXiv  Detail & Related papers  (2024-10-02T22:36:12Z)
• Universal Pooling Method of Multi-layer Features from Pretrained Models for Speaker Verification [7.005068872406135]
  Recent advancements in automatic speaker verification (ASV) studies have been achieved by leveraging large-scale pretrained networks. We present a novel approach for exploiting the multilayered nature of pretrained models for ASV. We show how the proposed interlayer processing aids in maximizing the advantage of utilizing pretrained models.
  arXiv  Detail & Related papers  (2024-09-12T05:55:32Z)
• FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detection [33.225938984092274]
  We propose a Foreground Self-Distillation (FSD) scheme that effectively avoids the issue of distribution discrepancies. We also design two Point Cloud Intensification ( PCI) strategies to compensate for the sparsity of point clouds. We develop a Multi-Scale Foreground Enhancement (MSFE) module to extract and fuse multi-scale foreground features.
  arXiv  Detail & Related papers  (2024-07-14T09:39:44Z)
• 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)
• Gradient Guidance for Diffusion Models: An Optimization Perspective [45.6080199096424]
  This paper studies a form of gradient guidance for adapting a pre-trained diffusion model towards optimizing user-specified objectives. We establish a mathematical framework for guided diffusion to systematically study its optimization theory and algorithmic design.
  arXiv  Detail & Related papers  (2024-04-23T04:51:02Z)
• Enhancing Generalization in Medical Visual Question Answering Tasks via Gradient-Guided Model Perturbation [16.22199565010318]
  We introduce a method that incorporates gradient-guided perturbations to the visual encoder of the multimodality model during both pre-training and fine-tuning phases. The results show that, even with a significantly smaller pre-training image caption dataset, our approach achieves competitive outcomes.
  arXiv  Detail & Related papers  (2024-03-05T06:57:37Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• Disentangled Pre-training for Image Matting [74.10407744483526]
  Image matting requires high-quality pixel-level human annotations to support the training of a deep model. We propose a self-supervised pre-training approach that can leverage infinite numbers of data to boost the matting performance.
  arXiv  Detail & Related papers  (2023-04-03T08:16:02Z)
• TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization [89.54947228958494]
  This paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks. We propose a novel statistics-based approach, Two-WIng NormliSation (TWINS) fine-tuning framework. TWINS is shown to be effective on a wide range of image classification datasets in terms of both generalization and robustness.
  arXiv  Detail & Related papers  (2023-03-20T14:12:55Z)
• General Greedy De-bias Learning [163.65789778416172]
  We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space. GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
  arXiv  Detail & Related papers  (2021-12-20T14:47:32Z)
• Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints [80.60538408386016]
  Estimating relative camera poses from consecutive frames is a fundamental problem in visual odometry. We propose an end-to-end trainable framework consisting of learnable modules for detection, feature extraction, matching and outlier rejection.
  arXiv  Detail & Related papers  (2020-07-29T21:41:31Z)

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.