Training A Multi-stage Deep Classifier with Feedback Signals
This addresses resource-limited industrial applications by improving training efficiency for multi-stage binary classifiers, though it is incremental as it builds on existing MSC methods.
The paper tackles the problem of training multi-stage classifiers (MSC) by proposing a Feedback Training framework that trains classifiers in reverse order using sample weighting from later stages, showing efficacy and superiority in few-shot scenarios.
Multi-Stage Classifier (MSC) - several classifiers working sequentially in an arranged order and classification decision is partially made at each step - is widely used in industrial applications for various resource limitation reasons. The classifiers of a multi-stage process are usually Neural Network (NN) models trained independently or in their inference order without considering the signals from the latter stages. Aimed at two-stage binary classification process, the most common type of MSC, we propose a novel training framework, named Feedback Training. The classifiers are trained in an order reverse to their actual working order, and the classifier at the later stage is used to guide the training of initial-stage classifier via a sample weighting method. We experimentally show the efficacy of our proposed approach, and its great superiority under the scenario of few-shot training.