Arya et al. suggest using either supervised or self-supervised learning techniques to train the NN; the former requires access to exact inference

Based on this, we believe that other classic9 methods would perform similarly to DeViSe if used instead in our GZSL semantic segmentation baseline. Yet, as abundantly exemplified in fully supervised learning, moving from image-level categorization to34 pixel-level recognition is not as direct or straightforward as it might seem. Moreover,toencode spatial context,37 we propose a novel graph convolutional generator which, conditioned on context graphs, generates corresponding38 structured pixel-level features. Also, as we shall clarify, our framework is not solely bound to GMMN as in [7]; it39 is in fact agnostic to the choice of the generative model.

We thank the reviewers for feedback, as well as efforts in reviewing. We respond to each comment below. Overall, there is no significant contribution to unsupervised pre-training. " The fact that our main contribution is a detailed procedure, rather than a theorem, architecture, or other artifact, We believe our contributions are significant. Indeed, R3 recognizes that "the simple semi-supervised framework is still I think it will inspire several future works." " While we believe ImageNet is a much more These results can be further improved with better augmentations during fine-tuning and an extra distillation step.

The performance of any supervised learning model depends strongly on the quality of input instances.