Name
Abstract | ||
|---|---|---|
In deep learning scenarios, a lot of labeled samples are needed to train the models. However, in practical application fields, since the objects to be recognized are complex and non-uniformly distributed, it is difficult to get enough labeled samples at one time. Active learning can actively improve the accuracy with fewer training labels, which is one of the promising solutions to tackle this problem. Inspired by human being's cognition process to acquire additional knowledge gradually, we propose a novel deep active learning method through Cognitive Information Parcels (CIPs) based on the analysis of model's cognitive errors and expert's instruction. The transformation of the cognitive parcels is defined, and the corresponding representation feature of the objects is obtained to identify the model's cognitive error information. Experiments prove that the samples, selected based on the CIPs, can benefit the target recognition and boost the deep model's performance efficiently. The characterization of cognitive knowledge can avoid the other samples' disturbance to the cognitive property of the model effectively. We believe that our work could provide a trial of thought about the cognitive knowledge used in deep learning field.
|
Year | DOI | Venue |
|---|---|---|
2017 | 10.1145/3123266.3123337 | MM '17: ACM Multimedia Conference
Mountain View
California
USA
October, 2017 |
Keywords | Field | DocType |
deep learning, active learning, cognitive information | Cognitive models of information retrieval,Active learning,Computer science,Artificial intelligence,Deep learning,Cognition,Machine learning | Conference |
ISBN | Citations | PageRank |
978-1-4503-4906-2 | 1 | 0.34 |
References | Authors | |
22 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wencang Zhao | 1 | 12 | 4.24 |
| Yu Kong | 2 | 412 | 24.72 |
| Zhengming Ding | 3 | 536 | 39.14 |
| Yun Fu | 4 | 4267 | 208.09 |