We propose Deep Companion Learning (DCL), a novel training method for Deep Neural Networks (DNNs) that enhances generalization by penalizing inconsistent model predictions compared to its historical performance. To achieve this, we train a deep-companion model (DCM), by using previous versions of the model to provide forecasts on new inputs. This companion model deciphers a meaningful latent semantic structure within the data, thereby providing targeted supervision that encourages the primary model to address the scenarios it finds most challenging. We validate our approach through both theoretical analysis and extensive experimentation, including ablation studies, on a variety of benchmark datasets (CIFAR-100, Tiny-ImageNet, ImageNet-1K) using diverse architectural models (ShuffleNetV2, ResNet, Vision Transformer, etc.), demonstrating state-of-the-art performance.

翻译：我们提出深度伴随学习（DCL），一种用于深度神经网络（DNN）的新型训练方法，该方法通过惩罚模型预测与其历史表现的不一致性来增强泛化能力。为实现这一目标，我们通过使用模型的先前版本来对新输入提供预测，从而训练一个深度伴随模型（DCM）。该伴随模型能够解析数据中有意义的潜在语义结构，从而提供有针对性的监督，促使主模型专注于处理其认为最具挑战性的场景。我们通过理论分析和广泛的实验验证了我们的方法，包括在各种基准数据集（CIFAR-100、Tiny-ImageNet、ImageNet-1K）上使用多种架构模型（ShuffleNetV2、ResNet、Vision Transformer等）进行的消融研究，证明了其最先进的性能。