In particular, we consider sequential prediction with an adversary that injects adversarial (or out-of-distribution) examples in a stream of i.i.d.

Furthermore, our self-supervised learning network is restricted to pre-train on the support set (comprising of scarce training examples) used to train the downstream network in a few-shot learning (FSL) setting. Finally, the fully-trained self-supervised network's point embeddings are input to the downstream task's network.

Ourmodel is trained in an EM-type manner alternating between increasing the 3D pose invariance ofthefeature extractor andannotating unlabelled data through neural viewsynthesis andmatching.

A prominent example of label-only privacy is in online advertising, where the goal is to predict conversionofanadimpression(thelabel)givenauser'sprofileandthespot'scontext(thefeatures).