基于神经聚类的视觉表示学习
Neural Clustering based Visual Representation Learning
AI总结：
提出神经聚类框架FEC，将特征提取视为从数据中选择代表的过程，通过迭代分组像素并更新深度特征自动捕获数据分布，在多种视觉识别任务中验证了其有效性与即席可解释性。
摘要：
我们通过重新审视聚类（机器学习和数据分析中最经典的方法之一），研究了机器视觉的一个基本方面：特征的度量。现有的视觉特征提取器，包括ConvNets、ViTs和MLPs，将图像表示为矩形区域。尽管这种网格范式很流行，但它建立在工程实践之上，缺乏对数据分布的显式建模。在本研究中，我们提出了特征提取与聚类（FEC），一个概念上优雅且出人意料地具有即席可解释性的神经聚类框架。它将特征提取视为从数据中选择代表的过程，从而自动捕获底层数据分布。给定一张图像，FEC在将像素分组为独立簇以抽象出代表，与使用当前代表更新像素的深度特征之间交替进行。这种迭代工作机制以若干神经层的形式实现，最终的代表可用于下游任务。跨层的聚类分配可供人类查看和检查，使FEC的前向过程完全透明，并赋予其出色的即席可解释性。在各种视觉识别模型和任务上的大量实验验证了FEC的有效性、通用性和可解释性。我们期望这项工作能引发对当前事实上的网格范式的重新思考。
英文摘要：
We investigate a fundamental aspect of machine vision: the measurement of features, by revisiting clustering, one of the most classic approaches in machine learning and data analysis. Existing visual feature extractors, including ConvNets, ViTs, and MLPs, represent an image as rectangular regions. Though prevalent, such a grid-style paradigm is built upon engineering practice and lacks explicit modeling of data distribution. In this work, we propose feature extraction with clustering (FEC), a conceptually elegant yet surprisingly ad-hoc interpretable neural clustering framework, which views feature extraction as a process of selecting representatives from data and thus automatically captures the underlying data distribution. Given an image, FEC alternates between grouping pixels into individual clusters to abstract representatives and updating the deep features of pixels with current representatives. Such an iterative working mechanism is implemented in the form of several neural layers and the final representatives can be used for downstream tasks. The cluster assignments across layers, which can be viewed and inspected by humans, make the forward process of FEC fully transparent and empower it with promising ad-hoc interpretability. Extensive experiments on various visual recognition models and tasks verify the effectiveness, generality, and interpretability of FEC. We expect this work will provoke a rethink of the current de facto grid-style paradigm.
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。
