Research map / Continual learning / Online and replay-based
DyTox: Transformers for Continual Learning With DYnamic TOken eXpansion
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DyTox instead of the evaluated baselines | ImageNet1000 continual learning · ImageNet1000 | performance | Helped |
| Use DyTox instead of other baselines | CIFAR100 continual learning · CIFAR100 | performance | Helped |
| Use DyTox instead of DER | continual learning across the evaluated step settings · evaluated benchmarks and step settings | performance | Mixed |
| Replace the transformer encoder with a ResNet (ablation) | DyTox · continual learning | performance | Hurt |
| Add MixUp (ablation) | DyTox · continual learning | forgetting | Helped |
| Add MixUp (ablation) | ResNet · continual learning | forgetting | Helped |
Closest papers by meaning
- Memory Efficient Continual Learning with Transformers (NeurIPS 2022 · similarity 0.88)
- Task-Free Dynamic Sparse Vision Transformer for Continual Learning (AAAI 2024 · similarity 0.87)
- Hyper-LifelongGAN: Scalable Lifelong Learning for Image Conditioned Generation (CVPR 2021 · similarity 0.87)
- Continual learning with hypernetworks (ICLR 2020 · similarity 0.87)
- TinySubNets: An Efficient and Low Capacity Continual Learning Strategy (AAAI 2025 · similarity 0.85)
- Task-Free Continual Generation and Representation Learning via Dynamic Expansionable Memory Cluster (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.