scholarly journals Special Issue on Large-Scale Computer Vision: Geometry, Inference, and Learning

2014 ◽  
Vol 110 (3) ◽  
pp. 241-242
Author(s):  
Roberto Cipolla ◽  
Carlo Colombo ◽  
Alberto Del Bimbo
2020 ◽  
Vol 1 ◽  
pp. 1961-1964
Author(s):  
Sami Muhaidat ◽  
Paschalis C. Sofotasios ◽  
Kaibin Huang ◽  
Muhammad Ali Imran ◽  
Zhiguo Ding ◽  
...  

Technologies ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 2
Author(s):  
Ashish Jaiswal ◽  
Ashwin Ramesh Babu ◽  
Mohammad Zaki Zadeh ◽  
Debapriya Banerjee ◽  
Fillia Makedon

Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudolabels as supervision and use the learned representations for several downstream tasks. Specifically, contrastive learning has recently become a dominant component in self-supervised learning for computer vision, natural language processing (NLP), and other domains. It aims at embedding augmented versions of the same sample close to each other while trying to push away embeddings from different samples. This paper provides an extensive review of self-supervised methods that follow the contrastive approach. The work explains commonly used pretext tasks in a contrastive learning setup, followed by different architectures that have been proposed so far. Next, we present a performance comparison of different methods for multiple downstream tasks such as image classification, object detection, and action recognition. Finally, we conclude with the limitations of the current methods and the need for further techniques and future directions to make meaningful progress.


Author(s):  
Steven McDonagh ◽  
Cigdem Beyan ◽  
Phoenix X Huang ◽  
Robert B Fisher
Keyword(s):  

Author(s):  
Cory F. Newman ◽  
Robert P. Reiser ◽  
Derek L. Milne

AbstractContributors to this Special Issue of the Cognitive Behaviour Therapist have considered the kind of infrastructure that should be in place to best support and guide CBT supervisors, providing practical advice and extensive procedural guidance. Here we briefly summarize and discuss in turn the 10 papers within this Special Issue, including suggestions for further enhancements. The first paper, by Milne and Reiser, conceptualized this infrastructure in terms of an ‘SOS’ (supporting our supervisors) framework, from identifying supervision competencies, to training, evaluation and feedback strategies. The next nine papers illustrate this framework with specific technical innovations, educational enhancements and procedural issues, or through comprehensive quality improvement systems, all designed to support supervisors. These papers suggest an assortment of workable infrastructure developments: two large-scale and comprehensive initiatives, some promising proposals and technologies, and a series of local, exploratory work. Collectively, they provide us with models for further developing evidence-based cognitive-behavioural supervision, and offer practical suggestions for giving supervisors the tools and support to maximize their supervisees’ learning, and to improve the associated client outcomes. Much research and development work remains to be done, and successful implementation will require institutional and political support, as well as cross-cultural adaptations. We conclude with an optimistic assessment of progress toward addressing some of the infrastructure improvements required to adequately support supervisors.


Sign in / Sign up

Export Citation Format

Share Document