Improving traffic sign recognition by active search
This work addresses the challenge of improving traffic-sign recognition for automated driving systems, though it is incremental as it builds on existing active-learning methods.
The paper tackles the problem of recognizing rare traffic signs by proposing an iterative active-learning algorithm that starts with a single sample of the rare class and efficiently identifies more samples from a large unlabeled set, achieving similar results even with synthetic data.
We describe an iterative active-learning algorithm to recognise rare traffic signs. A standard ResNet is trained on a training set containing only a single sample of the rare class. We demonstrate that by sorting the samples of a large, unlabeled set by the estimated probability of belonging to the rare class, we can efficiently identify samples from the rare class. This works despite the fact that this estimated probability is usually quite low. A reliable active-learning loop is obtained by labeling these candidate samples, including them in the training set, and iterating the procedure. Further, we show that we get similar results starting from a single synthetic sample. Our results are important as they indicate a straightforward way of improving traffic-sign recognition for automated driving systems. In addition, they show that we can make use of the information hidden in low confidence outputs, which is usually ignored.