What's Behind the Mask: Estimating Uncertainty in Image-to-Image Problems
원문 초록
Estimating uncertainty in image-to-image networks is an important task, particularly as such networks are being increasingly deployed in the biological and medical imaging realms. In this paper, we introduce a new approach to this problem based on masking. Given an existing image-to-image network, our approach computes a mask such that the distance between the masked reconstructed image and the masked true image is guaranteed to be less than a specified threshold, with high probability. The mask thus identifies the more certain regions of the reconstructed image. Our approach is agnostic to the underlying image-to-image network, and only requires triples of the input (degraded), reconstructed and true images for training. Furthermore, our method is agnostic to the distance metric used. As a result, one can use $L_p$-style distances or perceptual distances like LPIPS, which contrasts with interval-based approaches to uncertainty. Our theoretical guarantees derive from a conformal calibration procedure. We evaluate our mask-based approach to uncertainty on image colorization, image completion, and super-resolution tasks, demonstrating high quality performance on each.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A GAN-Enhanced Deep Learning Framework for Rooftop Detection from Historical Aerial Imagery
Leveraging the Powerful Attention of a Pre-trained Diffusion Model for Exemplar-based Image Colorization
MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization
Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
Controllable Image Colorization with Instance-aware Texts and Masks
Invertible Grayscale via Dual Features Ensemble
토론
이 논문과 연결된 포럼 글이 아직 없습니다.