Tag
This paper proposes Expert-Guided Mutual Distillation (EGMD) to address domain bias and semantic misalignment in multimodal fake news detection, achieving state-of-the-art accuracy and reducing domain bias by up to 57.3% across four datasets.
A novel patient-independent multimodal framework for automatic depression detection integrates BiLSTM with intra- and cross-modal attention and domain-adversarial training to improve generalization across speakers. It achieves state-of-the-art accuracy of 93.2% on the Androids-Corpus dataset.
OPERA proposes a multi-agent ensemble framework that treats expert weight assignment as an offline policy learning problem for universal biomedical image analysis, enabling test-time adaptation without retraining and consistently improving performance across 9 datasets and 30+ baselines.
Proposes PP-CPCANet, a covariance-free framework for domain generalization that learns a global orthogonal basis on the Stiefel manifold and achieves SOTA performance on four benchmarks.
This paper introduces hierarchical domain generalization, formalizing extrapolation from finite observed regions to an entire instance space. It shows that no matter how simple the hypothesis class, certain domain partitions make generalization impossible, arguing that modern generalization theory must incorporate domain structure.
FedCausal-Dyn is a novel federated learning framework that addresses dynamic feature drift by separating causal features from spurious variations, enabling robust prototype aggregation. It achieves state-of-the-art performance on federated domain generalization benchmarks.
This paper theoretically analyzes linear transformers for in-context learning under domain generalization, establishing dimension-independent convergence rates and proposing novel activation and loss designs for linearizing pretrained softmax LLMs.
Proposes a novel meta-learning strategy called MEDIC for open set domain generalization, which uses implicit gradient matching across domain and class splits to achieve better boundaries. Experiments show state-of-the-art performance.
UniPET is a universal network for PET image denoising that handles varying dose reduction factors using domain generalization and region-aware learning, achieving state-of-the-art performance.
This paper investigates whether code-switching ASR capabilities learned from limited seen language pairs can generalize to unseen pairs using model merging and domain generalization methods, finding only modest transfer.
This paper introduces Domain Generalizable Dataset Distillation (DGDD), a new problem setting that targets out-of-distribution generalization of distilled datasets, and proposes Spectral Gradient Surgery (SGS) to disentangle class-discriminative and domain-specific information by leveraging cross-domain gradient agreement in the spectral domain.
CPCANet is a domain generalization framework that uses Common Principal Component Analysis to discover structured domain-invariant subspaces, achieving state-of-the-art performance in zero-shot transfer.
This paper introduces MMDG-Bench, a unified benchmark for multimodal domain generalization that reveals limited progress in current methods and significant robustness challenges across diverse tasks.