Are Labels Necessary for Classifier Accuracy Evaluation?
share
To calculate the model accuracy on a computer vision task, e.g., object recognition, we usually require a test set composed of test samples and their ground truth labels. Whilst standard usage cases satisfy this requirement, many real-world scenarios involve unlabeled test data, rendering common model evaluation methods infeasible. We investigate this important and under-explored problem, Automatic model Evaluation (AutoEval). Specifically, given a labeled training set and a model, we aim to estimate the model accuracy on unlabeled test datasets. We construct a meta-dataset: a dataset comprised of datasets generated from the original training set via various image transformations such as rotation, background substitution, foreground scaling, etc. As the classification accuracy of the model on each sample (dataset) is known from the original dataset labels, our task can be solved via regression. Using the feature statistics to represent the distribution of a sample dataset, we can train regression techniques (e.g., a regression neural network) to predict model performance. Using synthetic meta-dataset and real-world datasets in training and testing, respectively, we report reasonable and promising estimates of the model accuracy. We also provide insights into the application scope, limitation, and future directions of AutoEval.
READ FULL TEXT
