paper-with-me

Papers

Attention Diversification for Domain Generalization

2022-10-09 · Rang Meng, Xianfeng Li, WeiJie Chen, Shicai Yang, Jie Song, Xinchao Wang, Lei Zhang, Mingli Song, Di Xie, ShiLiang Pu

Convolutional neural networks (CNNs) have demonstrated gratifying results at learning discriminative features. However, when applied to unseen domains, state-of-the-art models are usually prone to errors due to domain shift. After investigating this issue from the perspective of shortcut learning, we find the devils lie in the fact that models trained on different domains merely bias to different domain-specific features yet overlook diverse task-related features. Under this guidance, a novel Attention Diversification framework is proposed, in which Intra-Model and Inter-Model Attention Diversification Regularization are collaborated to reassign appropriate attention to diverse task-related features. Briefly, Intra-Model Attention Diversification Regularization is equipped on the high-level feature maps to achieve in-channel discrimination and cross-channel diversification via forcing different channels to pay their most salient attention to different spatial locations. Besides, Inter-Model Attention Diversification Regularization is proposed to further provide task-related attention diversification and domain-related attention suppression, which is a paradigm of "simulate, divide and assemble": simulate domain shift via exploiting multiple domain-specific models, divide attention maps into task-related and domain-related groups, and assemble them within each group respectively to execute regularization. Extensive experiments and analyses are conducted on various benchmarks to demonstrate that our method achieves state-of-the-art performance over other competing methods. Code is available at https://github.com/hikvision-research/DomainGeneralization.

📄 PDF Abstract BibTeX arXiv:2210.04206

Code (1)

hikvision-research/domaingeneralization 공식 구현 pytorch

Tasks

Domain Generalization

Similar Papers 제목 키워드 기반

Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization

2023-02-10 · Spandan Dey, Md Sahidullah, Goutam Saha

This work addresses the cross-corpora generalization issue for the low-resourced spoken language identification (LID) problem. We have conducted the experiments in the context of Indian LID and identified strikingly poor…

Data AugmentationDomain GeneralizationLanguage IdentificationSpoken language identification

Feature Diversification and Adaptation for Federated Domain Generalization

2024-07-11 · Seunghan Yang, Seokeon Choi, Hyunsin Park, Sungha Choi 외

Federated learning, a distributed learning paradigm, utilizes multiple clients to build a robust global model. In real-world applications, local clients often operate within their limited domains, leading to a `domain sh…

Domain GeneralizationFederated Learning

Unraveling the Key Components of OOD Generalization via Diversification

2023-12-26 · Harold Benoit, Liangze Jiang, Andrei Atanov, Oğuzhan Fatih Kar 외

Supervised learning datasets may contain multiple cues that explain the training set equally well, i.e., learning any of them would lead to the correct predictions on the training data. However, many of them can be spuri…

Multisource Collaborative Domain Generalization for Cross-Scene Remote Sensing Image Classification

2024-12-05 · Zhu Han, Ce Zhang, Lianru Gao, Zhiqiang Zeng 외

Cross-scene image classification aims to transfer prior knowledge of ground materials to annotate regions with different distributions and reduce hand-crafted cost in the field of remote sensing. However, existing approa…

DiversityDomain Generalizationimage-classificationImage Classification+3

$\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization

2024-10-07 · Dylan Zhang, Justin Wang, Francois Charton

Understanding and accurately following instructions is critical for large language models (LLMs) to be effective across diverse tasks. In this work, we rigorously examine the key factors that enable models to generalize …

DiversityInstruction Following