paper-with-me

Papers

AttentionLite: Towards Efficient Self-Attention Models for Vision

2020-12-21 · Souvik Kundu, Sairam Sundaresan

We propose a novel framework for producing a class of parameter and compute efficient models called AttentionLitesuitable for resource-constrained applications. Prior work has primarily focused on optimizing models either via knowledge distillation or pruning. In addition to fusing these two mechanisms, our joint optimization framework also leverages recent advances in self-attention as a substitute for convolutions. We can simultaneously distill knowledge from a compute-heavy teacher while also pruning the student model in a single pass of training thereby reducing training and fine-tuning times considerably. We evaluate the merits of our proposed approach on the CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets. Not only do our AttentionLite models significantly outperform their unoptimized counterparts in accuracy, we find that in some cases, that they perform almost as well as their compute-heavy teachers while consuming only a fraction of the parameters and FLOPs. Concretely, AttentionLite models can achieve upto30x parameter efficiency and 2x computation efficiency with no significant accuracy drop compared to their teacher.

📄 PDF Abstract BibTeX arXiv:2101.05216

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Stand-Alone Self-Attention in Vision Models

2019-06-13 · NeurIPS 2019 12 · Prajit Ramachandran, Niki Parmar, Ashish Vaswani, Irwan Bello 외

Convolutions are a fundamental building block of modern computer vision systems. Recent approaches have argued for going beyond convolutions in order to capture long-range dependencies. These efforts focus on augmenting …

object-detectionObject Detection

BOAT: Bilateral Local Attention Vision Transformer

2022-01-31 · Tan Yu, Gangming Zhao, Ping Li, Yizhou Yu

Vision Transformers achieved outstanding performance in many computer vision tasks. Early Vision Transformers such as ViT and DeiT adopt global self-attention, which is computationally expensive when the number of patche…

ViT-LSLA: Vision Transformer with Light Self-Limited-Attention

2022-10-31 · Zhenzhe Hechen, Wei Huang, Yixin Zhao

Transformers have demonstrated a competitive performance across a wide range of vision tasks, while it is very expensive to compute the global self-attention. Many methods limit the range of attention within a local wind…

Position

Lite Vision Transformer with Enhanced Self-Attention

2021-12-20 · CVPR 2022 1 · Chenglin Yang, Yilin Wang, Jianming Zhang, He Zhang 외

Despite the impressive representation capacity of vision transformer models, current light-weight vision transformer models still suffer from inconsistent and incorrect dense predictions at local regions. We suspect that…

Panoptic SegmentationSegmentationSemantic Segmentation

Axially Expanded Windows for Local-Global Interaction in Vision Transformers

2022-09-19 · Zhemin Zhang, Xun Gong

Recently, Transformers have shown promising performance in various vision tasks. A challenging issue in Transformer design is that global self-attention is very expensive to compute, especially for the high-resolution vi…