中文标题#
基於進化選擇微調的遷移學習優化
英文标题#
Transfer learning optimization based on evolutionary selective fine tuning
中文摘要#
深度學習在圖像分析方面取得了顯著進展。 然而，大型完全訓練模型的計算需求仍然是一個需要考慮的問題。 遷移學習提供了一種將預訓練模型適應到新任務的策略。 傳統的微調通常涉及更新所有模型參數，這可能導致過擬合和更高的計算成本。 本文介紹了 BioTune，這是一種進化自適應微調技術，可選擇性地微調層以提高遷移學習效率。 BioTune 採用進化算法來確定一組聚焦的層進行微調，旨在優化模型在給定目標任務上的性能。 在來自不同領域的九個圖像分類數據集上的評估表明，與現有的微調方法如 AutoRGN 和 LoRA 相比，BioTune 實現了具有競爭力或改進的準確性和效率。 通過將微調過程集中在相關層的一個子集上，BioTune 減少了可訓練參數的數量，可能降低計算成本，並促進在不同數據特徵和分佈下的更高效的遷移學習。
英文摘要#
Deep learning has shown substantial progress in image analysis. However, the computational demands of large, fully trained models remain a consideration. Transfer learning offers a strategy for adapting pre-trained models to new tasks. Traditional fine-tuning often involves updating all model parameters, which can potentially lead to overfitting and higher computational costs. This paper introduces BioTune, an evolutionary adaptive fine-tuning technique that selectively fine-tunes layers to enhance transfer learning efficiency. BioTune employs an evolutionary algorithm to identify a focused set of layers for fine-tuning, aiming to optimize model performance on a given target task. Evaluation across nine image classification datasets from various domains indicates that BioTune achieves competitive or improved accuracy and efficiency compared to existing fine-tuning methods such as AutoRGN and LoRA. By concentrating the fine-tuning process on a subset of relevant layers, BioTune reduces the number of trainable parameters, potentially leading to decreased computational cost and facilitating more efficient transfer learning across diverse data characteristics and distributions.
文章页面#
PDF 获取#
抖音掃碼查看更多精彩內容