Mykhaylo Andriluka
Mykhaylo Andriluka is a senior research scientist at Google. Previously he has
been a visiting assistant professor at Stanford University and a junior research
group leader at the Max-Planck Institute for Informatics. Mykhaylo holds a master's degree
in mathematics and PhD degree in computer science from TU Darmstadt. His
research interests are in various aspects of visual human analysis such as
articulated pose estimation and tracking, multi-person tracking, people
detection and activity recognition. Mykhaylos' work has received the best paper
awards at AMDO'12 and BMVC'12, and was a winning entry in the MOTChallenge'16
competition on multi-person tracking. Mykhaylo is also a co-creator of several
popular benchmarks for articulated human pose estimation.
Research Areas
Authored Publications
Sort By
Preview abstract
This paper aims to reduce the time to annotate images for panoptic
segmentation, which requires annotating segmentation masks and
class labels for all object instances and stuff regions. We formulate
our approach as a collaborative process between an annotator
and an automated assistant who take turns to jointly annotate an
image using a predefined pool of segments. Actions performed by
the annotator serve as a strong contextual signal. The assistant
intelligently reacts to this signal by annotating other parts of the
image on its own, which reduces the amount of work required by
the annotator. We perform thorough experiments on the COCO
panoptic dataset, both in simulation and with human annotators.
These demonstrate that our approach is significantly faster than
the recent machine-assisted interface of [4], and 2.4x to 5x faster
than manual polygon drawing. Finally, we show on ADE20k [62]
that our method can be used to efficiently annotate new datasets,
bootstrapping from a very small amount of annotated data.
View details
Preview abstract
We introduce Fluid Annotation, an intuitive human-machine collaboration interface for annotating the class label and outline of every object and background region in an image. Fluid Annotation starts from the output of a strong neural network model, which the annotator can edit by correcting the labels of existing regions, adding new regions to cover missing objects, and removing incorrect regions. Fluid annotation has several attractive properties: (a) it is very efficient in terms of human annotation time; (b) it supports full images annotation in a single pass, as opposed to performing a series of small tasks in isolation, such as indicating the presence of objects, clicking on instances, or segmenting a single object known to be present. Fluid Annotation subsumes all these tasks in one unified interface. (c) it empowers the annotator to choose what to annotate and in which order. This enables to put human effort only on the errors the machine made, which helps using the annotation budget effectively. Through extensive experiments on the COCO+Stuff dataset, we demonstrate that Fluid Annotation leads to accurate annotations very efficiently, taking three times less annotation time than the popular LabelMe interface.
View details