教CNN模拟人类视觉认知过程并正则化纹理-形状偏差
Teaching CNNs to mimic Human Visual Cognitive Process & regularise Texture-Shape bias
AI总结：
针对CNN存在纹理偏差、忽略全局形状特征的问题，提出受心理学启发的CognitiveCNN架构及正则化方法，平衡多模态特征影响，提升目标识别的准确率、鲁棒性与可解释性。
摘要：
计算机视觉领域的近期实验表明，纹理偏差是采用卷积神经网络（CNN）的模型取得优异结果的主要原因，这与早期声称这类网络利用形状识别物体的研究相矛盾。学界认为，代价函数迫使CNN采取贪心策略，逐渐倾向于纹理等局部信息以提升准确率，因此未能探究任何全局统计特征。受心理学特征整合理论启发，我们提出了一种直观的新型架构CognitiveCNN，利用形状、纹理、边缘等人类可解释特征来重建并分类图像。我们定义了新的度量指标，通过注意力图量化这些模态中“抽象信息”的“相关性”。我们进一步引入了一种正则化方法，确保形状、纹理等各模态在给定任务中发挥与其在重建任务中相当的比例影响；实验表明，该方法除了为这些CNN赋予可解释性以实现更优的目标识别性能外，还能提升准确率和鲁棒性。
英文摘要：
Recent experiments in computer vision demonstrate texture bias as the primary reason for supreme results in models employing Convolutional Neural Networks (CNNs), conflicting with early works claiming that these networks identify objects using shape. It is believed that the cost function forces the CNN to take a greedy approach and develop a proclivity for local information like texture to increase accuracy, thus failing to explore any global statistics. We propose CognitiveCNN, a new intuitive architecture, inspired from feature integration theory in psychology to utilise human interpretable feature like shape, texture, edges etc. to reconstruct, and classify the image. We define novel metrics to quantify the "relevance" of "abstract information" present in these modalities using attention maps. We further introduce a regularisation method which ensures that each modality like shape, texture etc. gets proportionate influence in a given task, as it does for reconstruction; and perform experiments to show the resulting boost in accuracy and robustness, besides imparting explainability to these CNNs for achieving superior performance in object recognition.
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。
