Claims: Although pose is an input to our model, no GT pose labels were used for training.

Weaknesses: - Most major parts in this work, such as distillation, fine-tuning are proposed in previous works. Although the authors improve SimCLR and proposed SimCLR V2, the novelties in individual parts are somehow limited. However, I think the simple semi-supervised framework is still valuable for industry and future works. It explicitly points out a previously ignored paradigm in semi-supervised visual learning where regularization based methods dominates. I think it will inspire several future works following the paradigm.

ICCV 2019 today announced its Best Paper Awards in three categories. The ICCV (IEEE International Conference on Computer Vision) is a top international biannual computer vision gathering comprising a main conference and several co-located workshops and tutorials. ICCV 2019 received 4,303 papers -- more than twice the number submitted to ICCV 2017 -- and accepted 1,075, for a reception rate of roughly 25 percent. Abstract: We introduce SinGAN, an unconditional generative model that can be learned from a single natural image. Our model is trained to capture the internal distribution of patches within the image, and is then able to generate high quality, diverse samples that carry the same visual content as the image.

The rapid progress in synthetic image generation and manipulation has now come to a point where it raises significant concerns on the implication on the society. At best,this leads to a loss of trust in digital content, but it might even cause further harm by spreading false information and the creation of fake news. In this paper, we examine the real-ism of state-of-the-art image manipulations, and how difficult it is to detect them – either automatically or by humans.In particular, we focus on DeepFakes, Face2Face, and FaceSwap as prominent representatives for facial manipulations. We create more than half a million manipulated images respectively for each approach. The resulting publicly available dataset is at least an order of magnitude larger than comparable alternatives and it enables us to train data-driven forgery detectors in a supervised fashion.