Short Course

Hamed Pirsiavash
Self-supervised learning for visual recognition

We are intrested in learning visual representation (features) that are discriminative for semantic image understanding tasks such as object classification, detection, and segmentation in images . A common approach to obtain such features is to use supervised learning. However, this requires manual annotation of images, which is costly, time-consuming, and prone to errors. in contrast, unsupervised or self-supervised feature learning methods exploiting unlabled data can be much more scalable and flexible. I will present some of our recent efforts in this direction.