CAPEEN：结合早退机制与知识蒸馏的图像描述生成
CAPEEN: Image Captioning with Early Exits and Knowledge Distillation
AI总结：
针对图像描述任务中深度神经网络推理延迟高的问题，提出结合知识蒸馏的早退模型CAPEEN及自适应变体A-CAPEEN，在保持性能的同时实现1.77倍加速并提升抗失真鲁棒性。
摘要：
深度神经网络（DNN）在图像描述任务的视觉元素识别与描述文本生成方面已取得显著进展，但其性能提升伴随着计算负担与推理延迟的增加。早退（Early Exit，EE）策略可用于提升效率，但由于图像描述需要不同层级的语义信息才能实现准确预测，该策略的适配在图像描述领域存在挑战。为解决这一问题，我们提出CAPEEN模型，通过知识蒸馏提升早退策略的性能。在CAPEEN的推理过程中，若预测置信度超过从训练数据中学习得到的预设阈值，推理将在中间层完成。考虑到实际部署场景中目标分布可能偏离训练样本分布，我们提出变体A-CAPEEN，利用多臂老虎机（Multiarmed bandits）框架动态调整阈值。在MS COCO和Flickr30k数据集上的实验表明，与最终层推理的模型相比，CAPEEN实现了1.77倍的加速，同时保持了具有竞争力的性能，而A-CAPEEN还具备对失真的鲁棒性。源代码可在https://github.com/Div290/CapEEN获取。
英文摘要：
Deep neural networks (DNNs) have made significant progress in recognizing visual elements and generating descriptive text in image-captioning tasks. However, their improved performance comes from increased computational burden and inference latency. Early Exit (EE) strategies can be used to enhance their efficiency, but their adaptation presents challenges in image captioning as it requires varying levels of semantic information for accurate predictions. To overcome this, we introduce CAPEEN to improve the performance of EE strategies using knowledge distillation. Inference in CAPEEN is completed at intermediary layers if prediction confidence exceeds a predefined value learned from the training data. To account for real-world deployments, where target distributions could drift from that of training samples, we introduce a variant A-CAPEEN to adapt the thresholds on the fly using Multiarmed bandits framework. Experiments on the MS COCO and Flickr30k datasets show that CAPEEN gains speedup of 1.77x while maintaining competitive performance compared to the final layer, and A-CAPEEN additionally offers robustness against distortions. The source code is available at https://github.com/Div290/CapEEN
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
