paper-with-me

홈 › Papers

PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers in a resource-limited Context

2024-10-23 · Maximilian Augustin, Syed Shakib Sarwar, Mostafa Elhoushi, Sai Qian Zhang, Yuecheng Li, Barbara De Salvo

Following their success in natural language processing (NLP), there has been a shift towards transformer models in computer vision. While transformers perform well and offer promising multi-tasking performance, due to their high compute requirements, many resource-constrained applications still rely on convolutional or hybrid models that combine the benefits of convolution and attention layers and achieve the best results in the sub 100M parameter range. Simultaneously, task adaptation techniques that allow for the use of one shared transformer backbone for multiple downstream tasks, resulting in great storage savings at negligible cost in performance, have not yet been adopted for hybrid transformers. In this work, we investigate how to achieve the best task-adaptation performance and introduce PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers. We further combine PETAH adaptation with pruning to achieve highly performant and storage friendly models for multi-tasking. In our extensive evaluation on classification and other vision tasks, we demonstrate that our PETAH-adapted hybrid models outperform established task-adaptation techniques for ViTs while requiring fewer parameters and being more efficient on mobile hardware.

📄 PDF Abstract BibTeX arXiv:2410.17661

Code (0)

등록된 구현이 없습니다.

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…
Pruning 설명 없음

Similar Papers 제목 키워드 기반

Where Should LoRA Go? Component-Type Placement in Hybrid Language Models

2026-04-24 · Hector Borobia, Elies Seguí-Mas, Guillermina Tormo-Carbó arxiv

Hybrid language models that interleave attention with recurrent components are increasingly competitive with pure Transformers, yet standard LoRA practice applies adapters uniformly without considering the distinct funct…

Parameter-efficient Model Adaptation for Vision Transformers

2022-03-29 · Xuehai He, Chunyuan Li, Pengchuan Zhang, Jianwei Yang 외

In computer vision, it has achieved great transfer learning performance via adapting large-scale pretrained vision models (e.g., vision transformers) to downstream tasks. Common approaches for model adaptation either upd…

BenchmarkingClassificationimage-classificationImage Classification+2

Gaze Estimation using Transformer

2021-05-30 · Yihua Cheng, Feng Lu

Recent work has proven the effectiveness of transformers in many computer vision tasks. However, the performance of transformers in gaze estimation is still unexplored. In this paper, we employ transformers and assess th…

Gaze Estimation

Hybrid Generative-Retrieval Transformers for Dialogue Domain Adaptation

2020-03-03 · Igor Shalyminov, Alessandro Sordoni, Adam Atkinson, Hannes Schulz

Domain adaptation has recently become a key problem in dialogue systems research. Deep learning, while being the preferred technique for modeling such systems, works best given massive training data. However, in the real…

Domain AdaptationResponse GenerationRetrieval

Vision transformers in domain adaptation and domain generalization: a study of robustness

2024-04-05 · Shadi Alijani, Jamil Fayyad, Homayoun Najjaran

Deep learning models are often evaluated in scenarios where the data distribution is different from those used in the training and validation phases. The discrepancy presents a challenge for accurately predicting the per…

Data AugmentationDomain AdaptationDomain GeneralizationMeta-Learning