Current person image retrieval methods have achieved great improvements in accuracy metrics. However, they rarely describe the reliability of the prediction. In this paper, we propose an Uncertainty-Aware Learning (UAL) method to remedy this issue. UAL aims at providing reliability-aware predictions by considering data uncertainty and model uncertainty simultaneously. Data uncertainty captures the ``noise" inherent in the sample, while model uncertainty depicts the model's confidence in the sample's prediction. Specifically, in UAL, (1) we propose a sampling-free data uncertainty learning method to adaptively assign weights to different samples during training, down-weighting the low-quality ambiguous samples. (2) we leverage the Bayesian framework to model the model uncertainty by assuming the parameters of the network follow a Bernoulli distribution. (3) the data uncertainty and the model uncertainty are jointly learned in a unified network, and they serve as two fundamental criteria for the reliability assessment: if a probe is high-quality (low data uncertainty) and the model is confident in the prediction of the probe (low model uncertainty), the final ranking will be assessed as reliable. Experiments under the risk-controlled settings and the multi-query settings show the proposed reliability assessment is effective. Our method also shows superior performance on three challenging benchmarks under the vanilla single query settings.
翻译:目前个人图像检索方法在准确度测量方面已取得了很大的改进,但很少能描述预测的可靠性。在本文件中,我们建议采用不确定性-软件学习方法来纠正这一问题。个人方法的目的是通过同时考虑数据不确定性和模型不确定性,提供可靠度预测,同时考虑数据不确定性和模型不确定性。数据不确定性捕捉了样本中固有的“噪音”,而模型不确定性则表明模型对样本预测的信心。具体地说,在个人指标方面,(1)我们建议采用无抽样数据不确定性学习方法,在培训期间为不同样本分配重量,降低低质量模糊样本的重量。 (2)我们利用贝叶西亚框架来模拟模型不确定性,假设网络的参数遵循伯努利分布模式。 (3)数据不确定性和模型不确定性是在一个统一的网络中共同学习的,而模型不确定性是可靠度评估的两个基本标准:如果探测器质量高(数据不确定性低),而且模型对探测器的预测有信心(模型不确定性低),则最后的排名将被评估为可靠。在风险-控制环境下进行的实验也显示高可靠性,而根据我们的三种标准,我们提出的可靠性的可靠度评估也显示高可靠性。