Object detection methods have witnessed impressive improvements in the last years thanks to the design of novel neural network architectures and the availability of large scale datasets.
We propose to handle these missing annotations by revisiting the standard knowledge distillation framework.
As opposed to existing approaches, that need to generate pseudo-labels offline, we use an auxiliary classifier, trained with image-level labels and regularized by the segmentation model, to obtain pseudo-supervision online and update the model incrementally.
Robotic visual systems operating in the wild must act in unconstrained scenarios, under different environmental conditions while facing a variety of semantic concepts, including unknown ones.
Current state of the art of anomaly segmentation uses generative models, exploiting their incapability to reconstruct patterns unseen during training.
While convolutional neural networks have brought significant advances in robot vision, their ability is often limited to closed world scenarios, where the number of semantic concepts to be recognized is determined by the available training set.