Recurrent Inference Machines for Solving Inverse Problems
This work addresses the need for more flexible and generalizable inference methods in machine learning, particularly for image restoration, by enabling learned algorithms without domain-specific constraints.
The authors tackled the problem of solving iterative inference problems by proposing Recurrent Inference Machines (RIM), a framework that trains recurrent neural networks to learn inference algorithms from data, achieving state-of-the-art performance on image denoising and super-resolution tasks.
Much of the recent research on solving iterative inference problems focuses on moving away from hand-chosen inference algorithms and towards learned inference. In the latter, the inference process is unrolled in time and interpreted as a recurrent neural network (RNN) which allows for joint learning of model and inference parameters with back-propagation through time. In this framework, the RNN architecture is directly derived from a hand-chosen inference algorithm, effectively limiting its capabilities. We propose a learning framework, called Recurrent Inference Machines (RIM), in which we turn algorithm construction the other way round: Given data and a task, train an RNN to learn an inference algorithm. Because RNNs are Turing complete [1, 2] they are capable to implement any inference algorithm. The framework allows for an abstraction which removes the need for domain knowledge. We demonstrate in several image restoration experiments that this abstraction is effective, allowing us to achieve state-of-the-art performance on image denoising and super-resolution tasks and superior across-task generalization.