Xiaoyu L.

We propose a method that can be applied to a pretrained classifier. Our method exploits a fidelity map estimate that is fused into the internal representations of the feature extractor, thereby guiding the attention of the network and making it more robust to noisy data. We improve the noisy-image classification results by significantly large margins, especially at high noise levels, and come close to the fully retrained approaches.

We propose a model-agnostic approach for reducing epistemic uncertainty while using a single pretrained network. We achieve this by tapping into the epistemic uncertainty through augmented and frequency-manipulated images to obtain denoised images with varying errors. We propose an ensemble method with two decoupled attention paths, over the pixel domain and over that of our different manipulations, to learn the final fusion. Our results significantly improve over the state-of-the-art baselines.