Prototypical parts-based models offer a "this looks like that" paradigm for intrinsic interpretability, yet they typically struggle with ImageNet-scale generalization and often require computationally expensive backbone finetuning. Furthermore, existing methods frequently suffer from "prototype drift," where learned prototypes lack tangible grounding in the training distribution and change their activation under small perturbations. We present ProtoQuant, a novel architecture that achieves prototype stability and grounded interpretability through latent vector quantization. By constraining prototypes to a discrete learned codebook within the latent space, we ensure they remain faithful representations of the training data without the need to update the backbone. This design allows ProtoQuant to function as an efficient, interpretable head that scales to large-scale datasets. We evaluate ProtoQuant on ImageNet and several fine-grained benchmarks (CUB-200, Cars-196). Our results demonstrate that ProtoQuant achieves competitive classification accuracy while generalizing to ImageNet and comparable interpretability metrics to other prototypical-parts-based methods.

翻译：基于原型部件的模型为内在可解释性提供了一种“此物似彼物”的范式，然而这类方法通常难以在ImageNet规模上实现泛化，且往往需要计算成本高昂的主干网络微调。此外，现有方法普遍存在“原型漂移”问题，即学习到的原型缺乏与训练分布的实际关联性，并在微小扰动下改变其激活模式。本文提出ProtoQuant，一种通过潜在向量量化实现原型稳定性和可解释性扎根的新型架构。通过将原型约束在潜在空间内离散化的学习码本中，我们确保其始终忠实表征训练数据，且无需更新主干网络。该设计使得ProtoQuant能够作为一个高效、可解释的头部网络，扩展至大规模数据集。我们在ImageNet及多个细粒度基准数据集（CUB-200、Cars-196）上评估ProtoQuant。实验结果表明，ProtoQuant在实现具有竞争力的分类精度的同时，能够泛化至ImageNet数据集，并在可解释性指标上达到与其他基于原型部件的方法相当的水平。