TL;DR
Adaptive Dual-Objective Feature Learning for Multimodal Domain Generalization (ADMMDG), a framework that separates feature learning into two complementary components: features that capture shared patterns with both modality and domain invariance, and modality specific features that preserve the unique characteristics of each modality while maintaining domain invariance.
Although SDG methods improve performance under highly domain distinguishable stylized shifts, they exhibit limited robustness to background, correlation and corruption shifts on larger datasets, and increased shape bias does not consistently yield enhanced OOD performance, thereby underscoring the need for further rese...
This work introduces MultiLoReFT, an efficient and scalable low-rank representation fine-tuning framework for multimodal learning with pretrained unimodal models that produces representations that support multimodal prediction while explicitly revealing how shared and modality-specific information is distributed across...
This paper develops a dynamic strategy that jointly optimizes modality fusion and alignment, and develops a learning-based strategy using a bi-level optimization framework and theoretically proves the convergence of the learning algorithm to ensure its reliability.
This work proposes CrossFeat, a framework that enables an existing monomodal descriptor to operate across modalities, and introduces a geometry-appearance disentanglement such that only appearance is altered while the geometric properties are preserved.
This work proposes a plug-and-play feature causality decomposition method for multimodal representation learning from causality perspective, which can be integrated into existing models with no affects on the original model structures.
This work proposes Retrv-MoE, a unified retrieval architecture built upon sparse Mixture-of-Experts (MoE), and theoretically and empirically demonstrates that this conditional computation mechanism provides a structural remedy to optimization interference by decoupling the learning trajectories of conflicting tasks and...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
