BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909214353391616 |
|---|---|
| author | Lee, Daeun Yoon, Jaehong Hwang, Sung Ju |
| author_facet | Lee, Daeun Yoon, Jaehong Hwang, Sung Ju |
| contents | Continual Test Time Adaptation (CTTA) is required to adapt efficiently to continuous unseen domains while retaining previously learned knowledge. However, despite the progress of CTTA, it is still challenging to deploy the model with improved forgetting-adaptation trade-offs and efficiency. In addition, current CTTA scenarios assume only the disjoint situation, even though real-world domains are seamlessly changed. To address these challenges, this paper proposes BECoTTA, an input-dependent and efficient modular framework for CTTA. We propose Mixture-of Domain Low-rank Experts (MoDE) that contains two core components: (i) Domain-Adaptive Routing, which helps to selectively capture the domain adaptive knowledge with multiple domain routers, and (ii) Domain-Expert Synergy Loss to maximize the dependency between each domain and expert. We validate that our method outperforms multiple CTTA scenarios, including disjoint and gradual domain shits, while only requiring ~98% fewer trainable parameters. We also provide analyses of our method, including the construction of experts, the effect of domain-adaptive experts, and visualizations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_08712 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation Lee, Daeun Yoon, Jaehong Hwang, Sung Ju Machine Learning Computer Vision and Pattern Recognition Continual Test Time Adaptation (CTTA) is required to adapt efficiently to continuous unseen domains while retaining previously learned knowledge. However, despite the progress of CTTA, it is still challenging to deploy the model with improved forgetting-adaptation trade-offs and efficiency. In addition, current CTTA scenarios assume only the disjoint situation, even though real-world domains are seamlessly changed. To address these challenges, this paper proposes BECoTTA, an input-dependent and efficient modular framework for CTTA. We propose Mixture-of Domain Low-rank Experts (MoDE) that contains two core components: (i) Domain-Adaptive Routing, which helps to selectively capture the domain adaptive knowledge with multiple domain routers, and (ii) Domain-Expert Synergy Loss to maximize the dependency between each domain and expert. We validate that our method outperforms multiple CTTA scenarios, including disjoint and gradual domain shits, while only requiring ~98% fewer trainable parameters. We also provide analyses of our method, including the construction of experts, the effect of domain-adaptive experts, and visualizations. |
| title | BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.08712 |