On Single Source Robustness in Deep Fusion Models
This work addresses a critical safety issue for applications like self-driving cars by improving model reliability against noisy inputs, though it is incremental as it builds on existing fusion methods.
The paper tackles the problem of ensuring robustness in deep fusion models against noise in a single input source, demonstrating that linear fusion lacks this guarantee and proposing a specialized loss with training algorithms and a convolutional fusion layer to achieve robustness while maintaining clean-data performance.
Algorithms that fuse multiple input sources benefit from both complementary and shared information. Shared information may provide robustness against faulty or noisy inputs, which is indispensable for safety-critical applications like self-driving cars. We investigate learning fusion algorithms that are robust against noise added to a single source. We first demonstrate that robustness against single source noise is not guaranteed in a linear fusion model. Motivated by this discovery, two possible approaches are proposed to increase robustness: a carefully designed loss with corresponding training algorithms for deep fusion models, and a simple convolutional fusion layer that has a structural advantage in dealing with noise. Experimental results show that both training algorithms and our fusion layer make a deep fusion-based 3D object detector robust against noise applied to a single source, while preserving the original performance on clean data.