Contextual fusion enhances robustness to image blurring
This addresses robustness issues in computer vision for applications requiring reliable performance under perturbations, though it appears incremental as it builds on existing CNN methods.
The researchers tackled the problem of deep neural networks' vulnerability to perturbations by developing a fusion model that combines background and foreground features from CNNs trained on different datasets. The model improved robustness to human-perceivable perturbations on MS COCO, particularly for classes with high context variability.
Mammalian brains handle complex reasoning by integrating information across brain regions specialized for particular sensory modalities. This enables improved robustness and generalization versus deep neural networks, which typically process one modality and are vulnerable to perturbations. While defense methods exist, they do not generalize well across perturbations. We developed a fusion model combining background and foreground features from CNNs trained on Imagenet and Places365. We tested its robustness to human-perceivable perturbations on MS COCO. The fusion model improved robustness, especially for classes with greater context variability. Our proposed solution for integrating multiple modalities provides a new approach to enhance robustness and may be complementary to existing methods.