Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs
[edit]
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:13411351, 2017.
Abstract
We approach structured output prediction by optimizing a deep value network (DVN) to precisely estimate the task loss on different output configurations for a given input. Once the model is trained, we perform inference by gradient descent on the continuous relaxations of the output variables to find outputs with promising scores from the value network. When applied to image segmentation, the value network takes an image and a segmentation mask as inputs and predicts a scalar estimating the intersection over union between the input and ground truth masks. For multilabel classification, the DVN’s objective is to correctly predict the F1 score for any potential label configuration. The DVN framework achieves the stateoftheart results on multilabel prediction and image segmentation benchmarks.
Related Material


