Choosing Wisely and Learning Deeply: Selective Cross-Modality Distillation via CLIP for Domain Generalization

• URL: http://arxiv.org/abs/2311.15145v3
• Date: Mon, 22 Apr 2024 03:32:18 GMT
• Title: Choosing Wisely and Learning Deeply: Selective Cross-Modality Distillation via CLIP for Domain Generalization
• Authors: Jixuan Leng, Yijiang Li, Haohan Wang,
• Abstract summary: Domain Generalization (DG) seeks to train models across multiple domains and test them on unseen ones. We introduce a novel approach, namely, Selective Cross-Modality Distillation for Domain Generalization (SCMD) SCMD leverages the capabilities of large vision-language models, specifically CLIP, to train a more efficient model. We assess SCMD's performance on various benchmarks, where it empowers a ResNet50 to deliver state-of-the-art performance.
• Score: 12.311957227670598
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Domain Generalization (DG), a crucial research area, seeks to train models across multiple domains and test them on unseen ones. In this paper, we introduce a novel approach, namely, Selective Cross-Modality Distillation for Domain Generalization (SCMD). SCMD leverages the capabilities of large vision-language models, specifically CLIP, to train a more efficient model, ensuring it acquires robust generalization capabilities across unseen domains. Our primary contribution is a unique selection framework strategically designed to identify hard-to-learn samples for distillation. In parallel, we introduce a novel cross-modality module that seamlessly combines the projected features of the student model with the text embeddings from CLIP, ensuring the alignment of similarity distributions. We assess SCMD's performance on various benchmarks, where it empowers a ResNet50 to deliver state-of-the-art performance, surpassing existing domain generalization methods. Furthermore, we provide a theoretical analysis of our selection strategy, offering deeper insight into its effectiveness and potential in the field of DG.

Related papers

• Multisource Collaborative Domain Generalization for Cross-Scene Remote Sensing Image Classification [57.945437355714155]
  Cross-scene image classification aims to transfer prior knowledge of ground materials to annotate regions with different distributions. Existing approaches focus on single-source domain generalization to unseen target domains. We propose a novel multi-source collaborative domain generalization framework (MS-CDG) based on homogeneity and heterogeneity characteristics of multi-source remote sensing data.
  arXiv  Detail & Related papers  (2024-12-05T06:15:08Z)
• Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts [56.57141696245328]
  In open-world scenarios, where both novel classes and domains may exist, an ideal segmentation model should detect anomaly classes for safety. Existing methods often struggle to distinguish between domain-level and semantic-level distribution shifts.
  arXiv  Detail & Related papers  (2024-11-06T11:03:02Z)
• LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization [61.16890890570814]
  Domain generalization (DG) methods aim to maintain good performance in an unseen target domain by using training data from multiple source domains. This work introduces a simple yet effective framework, dubbed learning from multiple experts (LFME) that aims to make the target model an expert in all source domains to improve DG.
  arXiv  Detail & Related papers  (2024-10-22T13:44:10Z)
• Learning to Generalize Unseen Domains via Multi-Source Meta Learning for Text Classification [71.08024880298613]
  We study the multi-source Domain Generalization of text classification. We propose a framework to use multiple seen domains to train a model that can achieve high accuracy in an unseen domain.
  arXiv  Detail & Related papers  (2024-09-20T07:46:21Z)
• Adaptive Domain Generalization via Online Disagreement Minimization [17.215683606365445]
  Domain Generalization aims to safely transfer a model to unseen target domains. AdaODM adaptively modifies the source model at test time for different target domains. Results show AdaODM stably improves the generalization capacity on unseen domains.
  arXiv  Detail & Related papers  (2022-08-03T11:51:11Z)
• A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification [49.548815417844786]
  Person re-identification (Re-ID) has achieved great success in the supervised scenario. It is difficult to directly transfer the supervised model to arbitrary unseen domains due to the model overfitting to the seen source domains. We propose MixNorm, which consists of domain-aware mix-normalization (DMN) and domain-ware center regularization (DCR)
  arXiv  Detail & Related papers  (2022-01-24T18:09:38Z)
• TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification [115.31432027711202]
  We argue that both domain-specific and domain-invariant features are crucial for improving the generalization ability of re-id models. We name two-stream adaptive learning (TAL) to simultaneously model these two kinds of information. Our framework can be applied to both single-source and multi-source domain generalization tasks.
  arXiv  Detail & Related papers  (2021-11-29T01:27:42Z)
• Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation [102.42638795864178]
  We propose a principled meta-learning based approach to OCDA for semantic segmentation. We cluster target domain into multiple sub-target domains by image styles, extracted in an unsupervised manner. A meta-learner is thereafter deployed to learn to fuse sub-target domain-specific predictions, conditioned upon the style code. We learn to online update the model by model-agnostic meta-learning (MAML) algorithm, thus to further improve generalization.
  arXiv  Detail & Related papers  (2020-12-15T13:21:54Z)
• Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation [9.265557367859637]
  Domain Generalization (DG) techniques aim to enhance such generalization capability of machine learning models. We propose Discriminative Adversarial Domain Generalization (DADG) with meta-learning-based cross-domain validation. Results show DADG consistently outperforms a strong baseline DeepAll, and outperforms the other existing DG algorithms in most of the evaluation cases.
  arXiv  Detail & Related papers  (2020-11-01T07:48:16Z)
• Generalizable Model-agnostic Semantic Segmentation via Target-specific Normalization [24.14272032117714]
  We propose a novel domain generalization framework for the generalizable semantic segmentation task. We exploit the model-agnostic learning to simulate the domain shift problem. Considering the data-distribution discrepancy between seen source and unseen target domains, we develop the target-specific normalization scheme.
  arXiv  Detail & Related papers  (2020-03-27T09:25:19Z)

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.