| Home | << 1 >> |
|
| Record | Links | |||||
|---|---|---|---|---|---|---|
Author  |
David Berga; Marc Masana; Joost Van de Weijer |
 
|
||||
| Title | Disentanglement of Color and Shape Representations for Continual Learning | Type | Conference Article | |||
| Year | 2020 | Publication | ICML Workshop on Continual Learning | Abbreviated Journal | ||
| Volume | Issue | Pages | ||||
| Keywords | ||||||
| Abstract | We hypothesize that disentangled feature representations suffer less from catastrophic forgetting. As a case study we perform explicit disentanglement of color and shape, by adjusting the network architecture. We tested classification accuracy and forgetting in a task-incremental setting with Oxford-102 Flowers dataset. We combine our method with Elastic Weight Consolidation, Learning without Forgetting, Synaptic Intelligence and Memory Aware Synapses, and show that feature disentanglement positively impacts continual learning performance. | |||||
| Address | Virtual; July 2020 | |||||
| Corporate Author | Thesis | |||||
| Publisher | Place of Publication | Editor | ||||
| Language | Summary Language | Original Title | ||||
| Series Editor | Series Title | Abbreviated Series Title | ||||
| Series Volume | Series Issue | Edition | ||||
| ISSN | ISBN | Medium | ||||
| Area | Expedition | Conference | ICMLW | |||
| Notes | LAMP; 600.120;CIC | Approved | no | |||
| Call Number | Admin @ si @ BMW2020 | Serial | 3506 | |||
| Permanent link to this record | ||||||