We present Mixture of Contrastive Experts (MiCE), a unified probabilistic
clustering framework that simultaneously exploits the discriminative
representations learned by contrastive learning and the semantic structures
captured by a latent mixture model. Motivated by the mixture of experts, MiCE
employs a gating function to partition an unlabeled dataset into subsets
according to the latent semantics and multiple experts to discriminate distinct
subsets of instances assigned to them in a contrastive learning manner. To
solve the nontrivial inference and learning problems caused by the latent
variables, we further develop a scalable variant of the
Expectation-Maximization (EM) algorithm for MiCE and provide proof of the
convergence. Empirically, we evaluate the clustering performance of MiCE on
four widely adopted natural image datasets. MiCE achieves significantly better
results than various previous methods and a strong contrastive learning
baseline.

MiCE 是一种可扩展的聚类框架，它同时利用了对比学习学习到的有区别的表示和混合模型捕捉的语义结构，通过 gating function 将一个未标记的数据集划分为子集，并使用多个专家以对比学习的方式区分分配给它们的不同子集的实例。我们进一步开发了 MiCE 的 EM 算法，通过实验证明了它在四个自然图像数据集上的性能显著优于以前的各种方法和强有力的对比学习基准。

MiCE: 无监督图像聚类的对比性专家混合

MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering

We propose a method for room layout estimation that does not rely on the
typical box approximation or Manhattan world assumption. Instead, we
reformulate the geometry inference problem as an instance detection task, which
we solve by directly regressing 3D planes using an R-CNN. We then use a variant
of probabilistic clustering to combine the 3D planes regressed at each frame in
a video sequence, with their respective camera poses, into a single global 3D
room layout estimate. Finally, we showcase results which make no assumptions
about perpendicular alignment, so can deal effectively with walls in any
alignment.

我们提出了一个不依赖于典型框近似或曼哈顿世界假设的房间布局估计方法，将几何推断问题重新定义为实例检测任务，通过使用 R-CNN 直接回归 3D 平面来解决该问题，然后使用一种概率聚类的变体来结合每个视频序列中的每帧回归的 3D 平面及其相应的相机姿态，并得到一个单个的全局 3D 房间布局估计结果；最后，我们展示了在不假设垂直对准的情况下处理任何对齐的墙壁的结果。

超越想象：生成无限制的三维房间布局

Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts

In this paper, we present a local information theoretic approach to
explicitly learn probabilistic clustering of a discrete random variable. Our
formulation yields a convex maximization problem for which it is NP-hard to
find the global optimum. In order to algorithmically solve this optimization
problem, we propose two relaxations that are solved via gradient ascent and
alternating maximization. Experiments on the MSR Sentence Completion Challenge,
MovieLens 100K, and Reuters21578 datasets demonstrate that our approach is
competitive with existing techniques and worthy of further investigation.

采用局部信息论方法显式地学习离散随机变量的概率聚类，并且通过渐近升级和交替升级算法来解决优化问题。 通过与现有技术的竞争和实验验证，表明该方法值得进一步研究。