paper-with-me

홈 › Papers

A4A: Adapter for Adapter Transfer via All-for-All Mapping for Cross-Architecture Models

2025-01-01 · CVPR 2025 1 · Keyu Tu, Mengqi Huang, Zhuowei Chen, Zhendong Mao

Large-scale text-to-image models evolve rapidly in size and architecture. The existing adapters struggle to keep pace with these models, requiring extensive retraining. This paper proposes a novel adapter transfer framework, A4A (Adapter for Adapter), which uses an all-for-all mapping approach to seamlessly transfer attention-based adapters across different model architectures (e.g., U-Net to transformer). The framework consists of Coupling Space Projection and Upgraded Space Mapping. During Coupling Space Projection, all attention features of the pretrained adapter are aggregated to fully capture the coupling relationship before being projected into a unified space. The unified space maintains coupling features in a consistent dimension, effectively and efficiently addressing feature scale discrepancies arising from the base model's architecture. In the Upgraded Space Mapping Module, randomly initialized learnable features are introduced to connect the unified and upgraded spaces by integrating reference features via the attention mechanism. The learned features are adaptively injected into the upgrade model through the Alignment module, which bridges the discrepancies between the models using the all-for-all mapping. Experimental results on personalized image generation tasks demonstrate that A4A outperforms previous methods in transferring adapters while being the first to achieve adapter transfer across model architectures.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

AllImage GenerationPersonalized Image Generation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
BASE 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
U-Net 설명 없음

Similar Papers 제목 키워드 기반

CDR-Adapter: Learning Adapters to Dig Out More Transferring Ability for Cross-Domain Recommendation Models

2023-11-04 · Yanyu Chen, Yao Yao, Wai Kin Victor Chan, Li Xiao 외

Data sparsity and cold-start problems are persistent challenges in recommendation systems. Cross-domain recommendation (CDR) is a promising solution that utilizes knowledge from the source domain to improve the recommend…

Recommendation SystemsTransfer Learning

Adaptable Adapters

2022-05-03 · NAACL 2022 7 · Nafise Sadat Moosavi, Quentin Delfosse, Kristian Kersting, Iryna Gurevych

State-of-the-art pretrained NLP models contain a hundred million to trillion parameters. Adapters provide a parameter-efficient alternative for the full finetuning in which we can only finetune lightweight neural network…

Adaptable Adapters

2022-01-16 · ACL ARR January 2022 1 · Anonymous

State-of-the-art pretrained NLP models contain a hundred million to trillion parameters. Adapters provide a parameter-efficient alternative for the full finetuning in which we can only finetune lightweight neural network…

MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer

2020-04-30 · EMNLP 2020 11 · Jonas Pfeiffer, Ivan Vulić, Iryna Gurevych, Sebastian Ruder

The main goal behind state-of-the-art pre-trained multilingual models such as multilingual BERT and XLM-R is enabling and bootstrapping NLP applications in low-resource languages through zero-shot or few-shot cross-lingu…

Cross-Lingual Transfernamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+2

Cross-Lingual Transfer with Target Language-Ready Task Adapters

2023-06-05 · Marinela Parović, Alan Ansell, Ivan Vulić, Anna Korhonen

Adapters have emerged as a modular and parameter-efficient approach to (zero-shot) cross-lingual transfer. The established MAD-X framework employs separate language and task adapters which can be arbitrarily combined to …

Cross-Lingual TransferZero-Shot Cross-Lingual Transfer