arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.01095cs.LGcs.AIcs.CVstat.ML
收藏

最小充分视图:基于更多证据进行预测的DNN模型具有更高的准确率

Minimal Sufficient Views: A DNN model making predictions with more evidence has higher accuracy

Toyota Central R&D Labs., Inc.(丰田中央研究实验室有限公司);DENSO CORPORATION(电装株式会社)

Keisuke Kawano, Takuro Kutsuna, Keisuke Sano

AI总结:

本研究提出最小充分视图(MSVs)来量化DNN发现的证据,发现证据数量与模型泛化性能强相关,并基于此提出无需标签的可靠模型选择指标。

摘要:

深度神经网络(DNNs)在图像识别中表现出高性能;然而,其强泛化能力的原因仍不清楚。一个合理的假设是,DNNs通过从图像中识别多个证据来实现鲁棒且准确的预测。因此,为了测试这一假设,本研究提出了最小充分视图(MSVs)。MSVs被定义为输入图像内一组最小的区域,这些区域足以保留DNNs的预测,从而代表DNN发现的证据。我们实证证明了MSVs的数量(即证据数量)与DNN模型的泛化性能之间存在强相关性。值得注意的是,这种相关性在单个DNN内部以及不同的DNNs之间(包括卷积和transformer模型)均成立。这表明基于更多证据进行预测的DNN模型具有更高的泛化性能。我们提出了一种基于MSVs的DNN模型选择指标,该指标不需要标签信息。因此,我们实证表明,所提出的指标对过拟合程度的依赖性较低,使其成为比现有指标(如平均置信度)更可靠的模型性能指标。

英文摘要:

Deep neural networks (DNNs) exhibit high performance in image recognition; however, the reasons for their strong generalization abilities remain unclear. A plausible hypothesis is that DNNs achieve robust and accurate predictions by identifying multiple pieces of evidence from images. Thus, to test this hypothesis, this study proposed minimal sufficient views (MSVs). MSVs is defined as a set of minimal regions within an input image that are sufficient to preserve the prediction of DNNs, thus representing the evidence discovered by the DNN. We empirically demonstrated a strong correlation between the number of MSVs (i.e., the number of pieces of evidence) and the generalization performance of the DNN models. Remarkably, this correlation was found to hold within a single DNN as well as between different DNNs, including convolutional and transformer models. This suggested that a DNN model that makes its prediction based on more evidence has a higher generalization performance. We proposed a metric based on MSVs for DNN model selection that did not require label information. Consequently, we empirically showed that the proposed metric was less dependent on the degree of overfitting, rendering it a more reliable indicator of model performance than existing metrics, such as average confidence.

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。

↑