Image recognition is a classic and common task in the computer vision field, which has been widely applied in the past decade. Most existing methods in literature aim to learn discriminative features from labeled images for classification, however, they generally neglect confounders that infiltrate into the learned features, resulting in low performances for discriminating test images. To address this problem, we propose a Recursive Counterfactual Deconfounding model for object recognition in both closed-set and open-set scenarios based on counterfactual analysis, called RCD. The proposed model consists of a factual graph and a counterfactual graph, where the relationships among image features, model predictions, and confounders are built and updated recursively for learning more discriminative features. It performs in a recursive manner so that subtler counterfactual features could be learned and eliminated progressively, and both the discriminability and generalization of the proposed model could be improved accordingly. In addition, a negative correlation constraint is designed for alleviating the negative effects of the counterfactual features further at the model training stage. Extensive experimental results on both closed-set recognition task and open-set recognition task demonstrate that the proposed RCD model performs better than 11 state-of-the-art baselines significantly in most cases.

翻译：图像识别是计算机视觉领域中经典且常见的任务，在过去十年中得到了广泛应用。现有文献中的大多数方法旨在从带标签图像中学习判别性特征进行分类，然而，它们通常忽略了渗入学习特征中的混杂因素，导致对测试图像的判别性能较低。为解决这一问题，本文基于反事实分析，提出了一种用于闭集和开集场景下目标识别的递归式反事实解耦模型（称为RCD）。该模型由事实图和反事实图组成，其中图像特征、模型预测和混杂因素之间的关系被递归地构建和更新，以学习更具判别性的特征。模型以递归方式运行，从而能够逐步学习并消除更细微的反事实特征，进而提升模型的判别能力和泛化能力。此外，在模型训练阶段设计了一种负相关约束，以进一步减轻反事实特征的负面影响。在闭集识别任务和开集识别任务上的大量实验结果表明，所提出的RCD模型在大多数情况下显著优于11种最先进的基线方法。