We address the problem of generalized category discovery (GCD) that aims to
partition a partially labeled collection of images; only a small part of the
collection is labeled and the total number of target classes is unknown. To
address this generalized image clustering problem, we revisit the mean-shift
algorithm, i.e., a classic, powerful technique for mode seeking, and
incorporate it into a contrastive learning framework. The proposed method,
dubbed Contrastive Mean-Shift (CMS) learning, trains an image encoder to
produce representations with better clustering properties by an iterative
process of mean shift and contrastive update. Experiments demonstrate that our
method, both in settings with and without the total number of clusters being
known, achieves state-of-the-art performance on six public GCD benchmarks
without bells and whistles.

我们提出了一种名为对比均值漂移（CMS）学习的方法，该方法在泛化图像聚类问题中使用经典而强大的均值漂移算法，并结合对比学习框架，通过均值漂移和对比更新的迭代过程来训练图像编码器，以产生具有更好聚类特性的表示。实验证明，在六个公共泛化类别发现基准测试中，我们的方法无论是在已知或未知总聚类数的设置下，都取得了最先进的性能，而无需使用其他技巧或方法。

对比均移学习用于广义类别发现

Contrastive Mean-Shift Learning for Generalized Category Discovery

Most recent self-supervised learning (SSL) algorithms learn features by
contrasting between instances of images or by clustering the images and then
contrasting between the image clusters. We introduce a simple mean-shift
algorithm that learns representations by grouping images together without
contrasting between them or adopting much of prior on the structure of the
clusters. We simply "shift" the embedding of each image to be close to the
"mean" of its neighbors. Since in our setting, the closest neighbor is always
another augmentation of the same image, our model will be identical to BYOL
when using only one nearest neighbor instead of 5 as used in our experiments.
Our model achieves 72.4% on ImageNet linear evaluation with ResNet50 at 200
epochs outperforming BYOL. Our code is available here:
this https URL

本研究提出一种基于平均漂移算法的自监督学习方法，通过将相邻的图像进行平移并聚合来学习图像的特征表示，无需对图像进行反向对比或采用较多的先验知识。该方法在 ImageNet 数据集上的线性评估中实现了 72.4% 的准确率，优于 BYOL 方法。

自监督学习的均值漂移

Mean Shift for Self-Supervised Learning

The mean-shift algorithm is a popular algorithm in computer vision and image
processing. It can also be cast as a minimum gamma-divergence estimation. In
this paper we focus on the "blurring" mean shift algorithm, which is one
version of the mean-shift process that successively blurs the dataset. The
analysis of the blurring mean-shift is relatively more complicated compared to
the nonblurring version, yet the algorithm convergence and the estimation
consistency have not been well studied in the literature. In this paper we
prove both the convergence and the consistency of the blurring mean-shift. We
also perform simulation studies to compare the efficiency of the blurring and
the nonblurring versions of the mean-shift algorithms. Our results show that
the blurring mean-shift has more efficiency.

本文中，我们聚焦于模糊均值漂移算法，并证明了其收敛性和一致性，并进行模拟研究比较了模糊和非模糊版本的均值漂移算法效率高低，结果表明，模糊均值漂移算法更加高效。