KIND: Knowledge Integration and Diversion for Training Decomposable Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913848305385472 |
|---|---|
| author | Xie, Yucheng Feng, Fu Shi, Ruixiao Wang, Jing Rui, Yong Geng, Xin |
| author_facet | Xie, Yucheng Feng, Fu Shi, Ruixiao Wang, Jing Rui, Yong Geng, Xin |
| contents | Pre-trained models have become the preferred backbone due to the increasing complexity of model parameters. However, traditional pre-trained models often face deployment challenges due to their fixed sizes, and are prone to negative transfer when discrepancies arise between training tasks and target tasks. To address this, we propose KIND, a novel pre-training method designed to construct decomposable models. KIND integrates knowledge by incorporating Singular Value Decomposition (SVD) as a structural constraint, with each basic component represented as a combination of a column vector, singular value, and row vector from U, Σ, and V^\top matrices. These components are categorized into learngenes for encapsulating class-agnostic knowledge and tailors for capturing class-specific knowledge, with knowledge diversion facilitated by a class gate mechanism during training. Extensive experiments demonstrate that models pre-trained with KIND can be decomposed into learngenes and tailors, which can be adaptively recombined for diverse resource-constrained deployments. Moreover, for tasks with large domain shifts, transferring only learngenes with task-agnostic knowledge, when combined with randomly initialized tailors, effectively mitigates domain shifts. Code will be made available at https://github.com/Te4P0t/KIND. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_07337 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KIND: Knowledge Integration and Diversion for Training Decomposable Models Xie, Yucheng Feng, Fu Shi, Ruixiao Wang, Jing Rui, Yong Geng, Xin Computer Vision and Pattern Recognition Pre-trained models have become the preferred backbone due to the increasing complexity of model parameters. However, traditional pre-trained models often face deployment challenges due to their fixed sizes, and are prone to negative transfer when discrepancies arise between training tasks and target tasks. To address this, we propose KIND, a novel pre-training method designed to construct decomposable models. KIND integrates knowledge by incorporating Singular Value Decomposition (SVD) as a structural constraint, with each basic component represented as a combination of a column vector, singular value, and row vector from U, Σ, and V^\top matrices. These components are categorized into learngenes for encapsulating class-agnostic knowledge and tailors for capturing class-specific knowledge, with knowledge diversion facilitated by a class gate mechanism during training. Extensive experiments demonstrate that models pre-trained with KIND can be decomposed into learngenes and tailors, which can be adaptively recombined for diverse resource-constrained deployments. Moreover, for tasks with large domain shifts, transferring only learngenes with task-agnostic knowledge, when combined with randomly initialized tailors, effectively mitigates domain shifts. Code will be made available at https://github.com/Te4P0t/KIND. |
| title | KIND: Knowledge Integration and Diversion for Training Decomposable Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.07337 |