Simplex Clustering via sBeta with Applications to Online Adjustment of Black-Box Predictions

by   Florent Chiaroni, et al.

We explore clustering the softmax predictions of deep neural networks and introduce a novel probabilistic clustering method, referred to as k-sBetas. In the general context of clustering distributions, the existing methods focused on exploring distortion measures tailored to simplex data, such as the KL divergence, as alternatives to the standard Euclidean distance. We provide a general perspective of clustering distributions, which emphasizes that the statistical models underlying distortion-based methods may not be descriptive enough. Instead, we optimize a mixed-variable objective measuring the conformity of data within each cluster to the introduced sBeta density function, whose parameters are constrained and estimated jointly with binary assignment variables. Our versatile formulation approximates a variety of parametric densities for modeling cluster data, and enables to control the cluster-balance bias. This yields highly competitive performances for efficient unsupervised adjustment of black-box predictions in a variety of scenarios, including one-shot classification and unsupervised domain adaptation in real-time for road segmentation. Implementation is available at


page 1

page 14


Local Prediction Aggregation: A Frustratingly Easy Source-free Domain Adaptation Method

We propose a simple but effective source-free domain adaptation (SFDA) m...

EXTERN: Leveraging Endo-Temporal Regularization for Black-box Video Domain Adaptation

To enable video models to be applied seamlessly across video tasks in di...

Centroid Networks for Few-Shot Clustering and Unsupervised Few-Shot Classification

Traditional clustering algorithms such as K-means rely heavily on the na...

PROPS: Probabilistic personalization of black-box sequence models

We present PROPS, a lightweight transfer learning mechanism for sequenti...

Deep Direct Likelihood Knockoffs

Predictive modeling often uses black box machine learning methods, such ...

Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation

In the classic setting of unsupervised domain adaptation (UDA), the labe...

Please sign up or login with your details

Forgot password? Click here to reset