• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

EER-ASSL: Combining Rollback Learning and Deep Learning for Rapid Adaptive Object Detection

Vol. 14, No. 12, December 31, 2020
10.3837/tiis.2020.12.009, Download Paper (Free):

Abstract

We propose a rapid adaptive learning framework for streaming object detection, called EER-ASSL. The method combines the expected error reduction (EER) dependent rollback learning and the active semi-supervised learning (ASSL) for a rapid adaptive CNN detector. Most CNN object detectors are built on the assumption of static data distribution. However, images are often noisy and biased, and the data distribution is imbalanced in a real world environment. The proposed method consists of collaborative sampling and EER-ASSL. The EER-ASSL utilizes the active learning (AL) and rollback based semi-supervised learning (SSL). The AL allows us to select more informative and representative samples measuring uncertainty and diversity. The SSL divides the selected streaming image samples into the bins and each bin repeatedly transfers the discriminative knowledge of the EER and CNN models to the next bin until convergence and incorporation with the EER rollback learning algorithm is achieved. The EER models provide a rapid short-term myopic adaptation and the CNN models an incremental long-term performance improvement. EER-ASSL can overcome noisy and biased labels in varying data distribution. Extensive experiments shows that EER-ASSL obtained 70.9 mAP compared to state-of-the-art technology such as Faster RCNN, SSD300, and YOLOv2.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
M. U. Ahmed, Y. H. Kim and P. K. Rhee, "EER-ASSL: Combining Rollback Learning and Deep Learning for Rapid Adaptive Object Detection," KSII Transactions on Internet and Information Systems, vol. 14, no. 12, pp. 4776-4794, 2020. DOI: 10.3837/tiis.2020.12.009.

[ACM Style]
Minhaz Uddin Ahmed, Yeong Hyeon Kim, and Phill Kyu Rhee. 2020. EER-ASSL: Combining Rollback Learning and Deep Learning for Rapid Adaptive Object Detection. KSII Transactions on Internet and Information Systems, 14, 12, (2020), 4776-4794. DOI: 10.3837/tiis.2020.12.009.