Knowledge Distillation
Collaborative Distillation
Introduced by Wang et al. in Collaborative Distillation for Ultra-Resolution Universal Style TransferCollaborative Distillation is a new knowledge distillation method (named Collaborative Distillation) for encoder-decoder based neural style transfer to reduce the number of convolutional filters. The main idea is underpinned by a finding that the encoder-decoder pairs construct an exclusive collaborative relationship, which is regarded as a new kind of knowledge for style transfer models.
Source: Collaborative Distillation for Ultra-Resolution Universal Style Transfer
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Decoder | 2 | 18.18% |
| Federated Learning | 1 | 9.09% |
| Image Classification | 1 | 9.09% |
| Emotion Recognition | 1 | 9.09% |
| Multimodal Sentiment Analysis | 1 | 9.09% |
| Combinatorial Optimization | 1 | 9.09% |
| Meta-Learning | 1 | 9.09% |
| Continual Learning | 1 | 9.09% |
| Facial Makeup Transfer | 1 | 9.09% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
