Robust Domain Generalization for Multi-modal Object Recognition
This work addresses domain generalization for multi-modal object recognition, which is an incremental improvement over existing vision-language methods.
The paper tackles the problem of domain generalization in multi-modal object recognition by addressing limitations in loss functions, backbone generality, and class-aware visual fusion, resulting in superior performance across multiple datasets.
In multi-label classification, machine learning encounters the challenge of domain generalization when handling tasks with distributions differing from the training data. Existing approaches primarily focus on vision object recognition and neglect the integration of natural language. Recent advancements in vision-language pre-training leverage supervision from extensive visual-language pairs, enabling learning across diverse domains and enhancing recognition in multi-modal scenarios. However, these approaches face limitations in loss function utilization, generality across backbones, and class-aware visual fusion. This paper proposes solutions to these limitations by inferring the actual loss, broadening evaluations to larger vision-language backbones, and introducing Mixup-CLIPood, which incorporates a novel mix-up loss for enhanced class-aware visual fusion. Our method demonstrates superior performance in domain generalization across multiple datasets.