让浅层网络先判断，深层只处理难例，提升推理效率与准确率
Confidence-gated training for efficient early-exit neural networks
- 仅在浅层判断不准时才向深层传播梯度，避免深层主导训练
- 在印度菠菜和时尚MNIST数据集上，平均推理成本降低，整体准确率提升
- 适合资源受限场景部署深度模型，无需额外计算开销
早期退出神经网络通过在中间层实现置信预测来降低推理成本。然而联合训练常导致梯度干扰，深层分类器主导优化过程。本文提出置信门控训练（CGT），仅当前置出口失败时才向深层传播梯度。该机制促使浅层分类器成为主要决策点，同时将深层保留给更难样本。通过使训练策略与推理时的策略对齐，CGT缓解了过度思考问题，提升早期退出准确率并保持高效性。在Indian Pines和Fashion-MNIST基准上的实验表明，CGT在降低平均推理成本的同时提升了整体准确率，为资源受限环境中的深度模型部署提供了实用解决方案。
原文摘要 · Abstract (English)
Early-exit neural networks reduce inference cost by enabling confident predictions at intermediate layers. However, joint training often leads to gradient interference, with deeper classifiers dominating optimization. We propose Confidence-Gated Training (CGT), a paradigm that conditionally propagates gradients from deeper exits only when preceding exits fail. This encourages shallow classifiers to act as primary decision points while reserving deeper layers for harder inputs. By aligning training with the inference-time policy, CGT mitigates overthinking, improves early-exit accuracy, and preserves efficiency. Experiments on the Indian Pines and Fashion-MNIST benchmarks show that CGT lowers average inference cost while improving overall accuracy, offering a practical solution for deploying deep models in resource-constrained environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。