Improving Domain Generalization with Domain Relations at ICLR 2024
Leveraging domain relations for out-of-domain generalization.
Towards Private and Generalizable Deep Neural Networks: A2XP for Domain Generalization
A2XP, a novel domain generalization method, preserves the privacy of the objective network architecture while achieving state-of-the-art performance by disentangling the problem into expert adaptation and attention-based generalization.
Transitive Vision-Language Prompt Learning for Enhancing Domain Generalization
A novel prompt learning strategy that leverages deep vision prompts to address domain invariance while utilizing language prompts to ensure class separability, coupled with adaptive weighting mechanisms to balance domain invariance and class separability.
Quantization-aware Training for Domain Generalization: Using Model Quantization to Improve Generalization in Deep Learning
Quantization-aware training (QAT), typically used for model compression, can surprisingly enhance domain generalization in deep learning by guiding the optimization process towards flatter minima in the loss landscape, making models less susceptible to overfitting and more robust to unseen data distributions.
Causal-Invariant Bayesian Neural Networks for Robust Domain Generalization in Image Recognition
Integrating causal principles and Bayesian neural networks can improve the robustness of image recognition models against distribution shifts, outperforming traditional methods by disentangling domain-invariant features and mitigating overfitting.
인과적 불변 베이지안 신경망을 이용한 강력한 도메인 일반화
본 논문에서는 딥러닝 모델의 도메인 일반화 능력을 향상시키기 위해 인과적 추론과 베이지안 신경망을 결합한 새로운 접근 방식을 제안합니다.
잊혀진 영역 일반화를 찾아서: 대규모 데이터셋 시대에서 진정한 OOD 성능 평가
대규모 웹 데이터셋으로 훈련된 CLIP 모델의 뛰어난 성능은 훈련 데이터에 포함된 광범위한 도메인의 이미지 때문이며, 이는 모델이 실제로 OOD 일반화 능력을 갖췄다기보다는 훈련 데이터의 다양성에 의존한다는 것을 의미한다.
START: A Saliency-Driven State Space Model for Domain Generalization
START, a novel state space model architecture, enhances domain generalization by using saliency-driven token-aware transformation to mitigate the accumulation of domain-specific features in input-dependent matrices.
START: Saliency-Driven Token-Aware Transformation을 사용한 일반화된 State Space Model
본 논문에서는 입력 종속 행렬 내의 도메인 특정 특징이 모델 일반화를 저해할 수 있다는 것을 이론적으로 분석하고, 이를 해결하기 위해 Saliency-Driven Token-Aware Transformation(START)을 제안하여 도메인 일반화 성능을 향상시킵니다.
Combating Frequency Shortcut Learning in Domain Generalization Using Adversarial Frequency Augmentation
This research paper introduces a novel approach to address the issue of frequency shortcut learning in domain generalization by dynamically manipulating the frequency characteristics of training data using adversarial augmentation techniques.
© 2024 by Linnk AI