Multiple-Exit Tuning: Towards Inference-Efficient Adaptation for Vision Transformer

• URL: http://arxiv.org/abs/2409.13999v1
• Date: Sat, 21 Sep 2024 03:25:18 GMT
• Title: Multiple-Exit Tuning: Towards Inference-Efficient Adaptation for Vision Transformer
• Authors: Zheng Liu, Jinchao Zhu, Nannan Li, Gao Huang,
• Abstract summary: We introduce an inference-efficient tuning method termed multiple-exit tuning (MET) MET integrates multiple exits into the pre-trained vision transformer (ViT) backbone. In inference stage, easy samples will exit at early exits and only hard enough samples will flow to the last exit, thus saving the computational cost for easy samples.
• Score: 47.85315815897107
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Parameter-efficient transfer learning (PETL) has shown great potential in adapting a vision transformer (ViT) pre-trained on large-scale datasets to various downstream tasks. Existing studies primarily focus on minimizing the number of learnable parameters. Although these methods are storage-efficient, they allocate excessive computational resources to easy samples, leading to inefficient inference. To address this issue, we introduce an inference-efficient tuning method termed multiple-exit tuning (MET). MET integrates multiple exits into the pre-trained ViT backbone. Since the predictions in ViT are made by a linear classifier, each exit is equipped with a linear prediction head. In inference stage, easy samples will exit at early exits and only hard enough samples will flow to the last exit, thus saving the computational cost for easy samples. MET consists of exit-specific adapters (E-adapters) and graph regularization. E-adapters are designed to extract suitable representations for different exits. To ensure parameter efficiency, all E-adapters share the same down-projection and up-projection matrices. As the performances of linear classifiers are influenced by the relationship among samples, we employ graph regularization to improve the representations fed into the classifiers at early exits. Finally, we conduct extensive experiments to verify the performance of MET. Experimental results show that MET has an obvious advantage over the state-of-the-art methods in terms of both accuracy and inference efficiency.

Related papers

• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts. Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning [101.81127587760831]
  Current fine-tuning methods build adapters widely of the context of downstream task to learn, or the context of important knowledge to maintain. We propose CorDA, a Context-oriented Decomposition Adaptation method that builds learnable task-aware adapters. Our method enables two options, the knowledge-preserved adaptation and the instruction-previewed adaptation.
  arXiv  Detail & Related papers  (2024-06-07T19:10:35Z)
• Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation [67.13876021157887]
  Dynamic Tuning (DyT) is a novel approach to improve both parameter and inference efficiency for ViT adaptation. DyT achieves superior performance compared to existing PEFT methods while evoking only 71% of their FLOPs on the VTAB-1K benchmark.
  arXiv  Detail & Related papers  (2024-03-18T14:05:52Z)
• Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning [30.251155072822055]
  Prototype-based HyperAdapter (PHA) is a novel framework built on the adapter-tuning and hypernetwork. It introduces an instance-dense retriever and prototypical hypernetwork to generate conditional modules in a sample-efficient manner. We show that PHA strikes a better trade-off between trainable parameters, accuracy on stream tasks, and sample efficiency.
  arXiv  Detail & Related papers  (2023-10-18T02:42:17Z)
• Approximated Prompt Tuning for Vision-Language Pre-trained Models [54.326232586461614]
  In vision-language pre-trained models, prompt tuning often requires a large number of learnable tokens to bridge the gap between the pre-training and downstream tasks. We propose a novel Approximated Prompt Tuning (APT) approach towards efficient VL transfer learning.
  arXiv  Detail & Related papers  (2023-06-27T05:43:47Z)
• AdapterEM: Pre-trained Language Model Adaptation for Generalized Entity Matching using Adapter-tuning [3.4754314910585626]
  We propose a parameter-efficient paradigm for fine-tuning PrLMs based on adapters. We show that our solution achieves comparable or superior performance to full-scale PrLM fine-tuning and prompt-tuning baselines.
  arXiv  Detail & Related papers  (2023-05-30T04:03:23Z)
• AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks [55.705355299065474]
  Transformer-based pre-trained models with millions of parameters require large storage. Recent approaches tackle this shortcoming by training adapters, but these approaches still require a relatively large number of parameters. In this study, AdapterBias, a surprisingly simple yet effective adapter architecture, is proposed.
  arXiv  Detail & Related papers  (2022-04-30T16:49:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.