3 papers
cs.CV2019
Unaligned Image-to-Sequence Transformation with Loop Consistency
Siyang Wang, Justin Lazarow, Kwonjoon Lee +1
We tackle the problem of modeling sequential visual phenomena. Given examples of a phenomena that can be divided into discrete time steps, we aim to take an input from any such tim…
cs.CV2019
Learning Instance Occlusion for Panoptic Segmentation
Justin Lazarow, Kwonjoon Lee, Kunyu Shi +1
Panoptic segmentation requires segments of both "things" (countable object instances) and "stuff" (uncountable and amorphous regions) within a single output. A common approach invo…
cs.CV2019
Meta-Learning with Differentiable Convex Optimization
Kwonjoon Lee, Subhransu Maji, Avinash Ravichandran +1
Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively traine…