Feedback-prop: Convolutional Neural Network Inference under Partial Evidence
This addresses the challenge of improving inference accuracy in visual recognition tasks when incomplete data is provided, though it appears incremental as it builds on existing multi-task models.
The paper tackles the problem of performing inference in convolutional neural networks when only partial evidence is available, proposing a feedback-prop method that boosts prediction accuracy for unknown labels by leveraging known labels without retraining, achieving effectiveness across various multi-task models.
We propose an inference procedure for deep convolutional neural networks (CNNs) when partial evidence is available. Our method consists of a general feedback-based propagation approach (feedback-prop) that boosts the prediction accuracy for an arbitrary set of unknown target labels when the values for a non-overlapping arbitrary set of target labels are known. We show that existing models trained in a multi-label or multi-task setting can readily take advantage of feedback-prop without any retraining or fine-tuning. Our feedback-prop inference procedure is general, simple, reliable, and works on different challenging visual recognition tasks. We present two variants of feedback-prop based on layer-wise and residual iterative updates. We experiment using several multi-task models and show that feedback-prop is effective in all of them. Our results unveil a previously unreported but interesting dynamic property of deep CNNs. We also present an associated technical approach that takes advantage of this property for inference under partial evidence in general visual recognition tasks.