具有置信度自适应的任意时间稠密预测
Anytime Dense Prediction with Confidence Adaptivity
摘要:
任何时间推理需要一个模型来进行一系列可能在任何时间停止的预测。以往的研究主要集中在图像分类上。我们提出了第一个统一的端到端的方法,用于随时密集预测。一系列的“出口”被附加到模型上,以进行多个预测。我们重新设计了出口,以考虑每个出口的深度和空间分辨率。为了减少总计算量,并充分利用先前的预测,我们开发了一种新的空间自适应方法,以避免进一步计算的区域,早期的预测已经足够有信心。我们的完整方法,命名为任何时候密集预测的信心(ADP-C),达到了相同的最终精度水平的基础模型,同时显着减少总计算。我们评估了我们的方法在城市景观语义分割和MPII人体姿态估计:ADP-C可以随时推断,而不会牺牲准确性,同时还减少了44.4%和59.1%的基础模型的总FLOPs。我们比较了深度平衡网络和基于特征的随机采样的任何时间推断,表明ADP-C在准确性计算曲线上都占主导地位。我们的代码可在https://github.com/liuzhuang13/anytime上获得。
英文摘要:
Anytime inference requires a model to make a progression of predictions which might be halted at any time. Prior research on anytime visual recognition has mostly focused on image classification. We propose the first unified and end-to-end approach for anytime dense prediction. A cascade of "exits" is attached to the model to make multiple predictions. We redesign the exits to account for the depth and spatial resolution of the features for each exit. To reduce total computation, and make full use of prior predictions, we develop a novel spatially adaptive approach to avoid further computation on regions where early predictions are already sufficiently confident. Our full method, named anytime dense prediction with confidence (ADP-C), achieves the same level of final accuracy as the base model, and meanwhile significantly reduces total computation. We evaluate our method on Cityscapes semantic segmentation and MPII human pose estimation: ADP-C enables anytime inference without sacrificing accuracy while also reducing the total FLOPs of its base models by 44.4% and 59.1%. We compare with anytime inference by deep equilibrium networks and feature-based stochastic sampling, showing that ADP-C dominates both across the accuracy-computation curve. Our code is available at https://github.com/liuzhuang13/anytime .
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。