Special Issue on Learning with Fewer Labels in Computer Vision Call for Papers

 

Call For Papers 

IEEE Transactions on Pattern Analysis and Machine Intelligence 

Special Issue on Learning with Fewer Labels in Computer Vision 

 

 

1.         Abstract and Motivation 

The past several years have witnessed an explosion of interest in and
a dizzyingly fast development of machine learning, a subfield of
artificial intelligence. Foremost among these approaches are Deep
Neural Networks (DNNs) that can learn powerful feature representations
with multiple levels of abstraction directly from data when large
amounts of labeled data is available.  One of the core computer vision
areas, namely, object classification achieved a significant breakthrough
result with a deep convolutional neural network and the large scale
ImageNet dataset, which is arguably what reignited the field of
artificial neural networks and triggered the recent revolution in
Artificial Intelligence (AI). Nowadays, artificial intelligence has
spread over almost all fields of science and technology. Yet, computer
vision remains in the heart of these advances when it comes to visual
data analysis, offering the biggest big data and enabling advanced AI
solutions to be developed.

Undoubtedly, DNNs have shown remarkable success in many computer
vision tasks, such as recognizing/localizing/segmenting faces,
persons, objects, scenes, actions and gestures, and recognizing human
expressions, emotions, as well as object relations and interactions in
images or videos. Despite a wide range of impressive results, current
DNN based methods typically depend on massive amounts of accurately
annotated training data to achieve high performance, and are brittle
in that their performance can degrade severely with small changes in
their operating environment. Generally, collecting large scale
training datasets is time-consuming, costly, and in many applications
even infeasible, as for certain fields only very limited or no examples
at all can be gathered (such as visual inspection or medical domain),
although for some computer vision tasks large amounts of unlabeled
data may be relatively easy to collect, e.g., from the web or via
synthesis. Nevertheless, labeling and vetting massive amounts of
real-world training data is certainly difficult, expensive, or
time-consuming, as it requires the painstaking efforts of experienced
human annotators or experts, and in many cases prohibitively costly or
impossible due to some reason, such as privacy, safety or ethic issues
(e.g., endangered species, drug discovery, medical diagnostics and
industrial inspection).

DNNs lack the ability of learning from limited exemplars and fast
generalizing to new tasks. However, real-word computer vision
applications often require models that are able to (a) learn with few
annotated samples, and (b) continually adapt to new data without
forgetting prior knowledge. By contrast, humans can learn from just
one or a handful of examples (i.e., few shot learning), can do very
long-term learning, and can form abstract models of a situation and
manipulate these models to achieve extreme generalization. As a
result, one of the next big challenges in computer vision is to
develop learning approaches that are capable of addressing the
important shortcomings of existing methods in this regard. Therefore,
in order to address the current inefficiency of machine learning, there
is pressing need to research methods, (1) to drastically reduce
requirements for labeled training data, (2) to significantly reduce the
amount of data necessary to adapt models to new environments, and (3)
to even use as little labeled training data as people need.

 

2.         Topics of Interest 

This special issue focuses on learning with fewer labels for computer
vision tasks such as image classification, object detection, semantic
segmentation, instance segmentation, and many others and the topics of
interest include (but are not limited to) the following areas:

    Self-supervised learning methods 
    New methods for few-/zero-shot learning 
    Meta-learning methods 
    Life-long/continual/incremental learning methods 
    Novel domain adaptation methods 
    Semi-supervised learning methods 
    Weakly-supervised learning methods 

3.         Submission Deadline 

Paper Submission Deadline: April 15, 2021. 

4.         Guest Editors 

    Li Liu 

Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Finland 

li.liu@oulu.fi 

    Timothy Hospedales 

Professor 

University of Edinburgh, UK 

Principal Scientist at Samsung AI Research Centre Alan Turing Institute Fellow  

t.hospedales@ed.ac.uk 

    Yann LeCun 

Silver Professor 

New York University, United States  

VP and Chief AI Scientist at Facebook  

yann@fb.com 

    Mingsheng Long 

Tsinghua University, China  

mingsheng@tsinghua.edu.cn 

    Jiebo Luo 

Professor 

University of Rochester, United States  

jluo@cs.rochester.edu 

    Wanli Ouyang 

University of Sydney, Australia  

wanli.ouyang@sydney.edu.au 

    Matti Pietikäinen 

Professor (IEEE Fellow) 

Center for Machine Vision and Signal Analysis University of Oulu, Finland  

matti.pietikainen@oulu.fi 

    Tinne Tuytelaars 

Professor 

KU Leuven, Belgium  

Tinne.Tuytelaars@esat.kuleuven.be 

 

Main Contact: 

Dr. Li Liu 

Email: li.liu@oulu.fi, dreamliu2010@gmail.com 

National University of Defense Technology, China 

Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Finland