Multiple Instance Learning with Differential Evolutionary Pooling
While implementing Multiple Instance Learning (MIL) through Deep Neural Networks, the most important task is to design the bag-level pooling function that defines the instance-to-bag relationship and eventually determines the class label of a bag. In this article, Differential Evolutionary (DE) pool...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/12/1403 |
| _version_ | 1797530582966599680 |
|---|---|
| author | Kamanasish Bhattacharjee Arti Tiwari Millie Pant Chang Wook Ahn Sanghoun Oh |
| author_facet | Kamanasish Bhattacharjee Arti Tiwari Millie Pant Chang Wook Ahn Sanghoun Oh |
| author_sort | Kamanasish Bhattacharjee |
| collection | DOAJ |
| description | While implementing Multiple Instance Learning (MIL) through Deep Neural Networks, the most important task is to design the bag-level pooling function that defines the instance-to-bag relationship and eventually determines the class label of a bag. In this article, Differential Evolutionary (DE) pooling—an MIL pooling function based on Differential Evolution (DE) and a bio-inspired metaheuristic—is proposed for the optimization of the instance weights in parallel with training the Deep Neural Network. This article also presents the effects of different parameter adaptation techniques with different variants of DE on MIL. |
| first_indexed | 2024-03-10T10:31:03Z |
| format | Article |
| id | doaj.art-3040e7e21f004402a6d3593ec03620c5 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T10:31:03Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-3040e7e21f004402a6d3593ec03620c52023-11-21T23:38:17ZengMDPI AGElectronics2079-92922021-06-011012140310.3390/electronics10121403Multiple Instance Learning with Differential Evolutionary PoolingKamanasish Bhattacharjee0Arti Tiwari1Millie Pant2Chang Wook Ahn3Sanghoun Oh4Department of Applied Science & Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, IndiaDepartment of Applied Science & Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, IndiaDepartment of Applied Science & Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, IndiaAI Graduate School, Gwangju Institute of Science & Technology, Gwangju 61005, KoreaDepartment of Computer Science, Korea National Open University, Seoul 03087, KoreaWhile implementing Multiple Instance Learning (MIL) through Deep Neural Networks, the most important task is to design the bag-level pooling function that defines the instance-to-bag relationship and eventually determines the class label of a bag. In this article, Differential Evolutionary (DE) pooling—an MIL pooling function based on Differential Evolution (DE) and a bio-inspired metaheuristic—is proposed for the optimization of the instance weights in parallel with training the Deep Neural Network. This article also presents the effects of different parameter adaptation techniques with different variants of DE on MIL.https://www.mdpi.com/2079-9292/10/12/1403Multiple Instance Learning (MIL)Differential Evolution (DE)poolingadaptivevariantparameter |
| spellingShingle | Kamanasish Bhattacharjee Arti Tiwari Millie Pant Chang Wook Ahn Sanghoun Oh Multiple Instance Learning with Differential Evolutionary Pooling Electronics Multiple Instance Learning (MIL) Differential Evolution (DE) pooling adaptive variant parameter |
| title | Multiple Instance Learning with Differential Evolutionary Pooling |
| title_full | Multiple Instance Learning with Differential Evolutionary Pooling |
| title_fullStr | Multiple Instance Learning with Differential Evolutionary Pooling |
| title_full_unstemmed | Multiple Instance Learning with Differential Evolutionary Pooling |
| title_short | Multiple Instance Learning with Differential Evolutionary Pooling |
| title_sort | multiple instance learning with differential evolutionary pooling |
| topic | Multiple Instance Learning (MIL) Differential Evolution (DE) pooling adaptive variant parameter |
| url | https://www.mdpi.com/2079-9292/10/12/1403 |
| work_keys_str_mv | AT kamanasishbhattacharjee multipleinstancelearningwithdifferentialevolutionarypooling AT artitiwari multipleinstancelearningwithdifferentialevolutionarypooling AT milliepant multipleinstancelearningwithdifferentialevolutionarypooling AT changwookahn multipleinstancelearningwithdifferentialevolutionarypooling AT sanghounoh multipleinstancelearningwithdifferentialevolutionarypooling |