SiamMM: A Mixture Model Perspective on Deep Unsupervised Learning
Not on the map. Why?
Abstract (arXiv)
Recent studies have demonstrated the effectiveness of clustering-based approaches for self-supervised and unsupervised learning. However, the application of clustering is often heuristic, and the optimal methodology remains unclear. In this work, we establish connections between these unsupervised clustering methods and classical mixture models from statistics. Through this framework, we demonstrate significant enhancements to these clustering methods, leading to the development of a novel model named SiamMM. Our method attains state-of-the-art performance across various self-supervised learning benchmarks. Inspection of the learned clusters reveals a strong resemblance to unseen ground truth labels, uncovering potential instances of mislabeling.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 57 references that are in the map. First posted on arXiv 7 Nov 2025.
Builds on
34 of 57 references.
References · 34
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
- 2020Exploring Simple Siamese Representation Learningcited by 2,866
- 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
- 2017Billion-scale similarity search with GPUscited by 2,497
- 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
- 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
- 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
- 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
22 more
- 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
- 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
- 2019Contrastive Multiview Codingcited by 1,301
- 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,057
- 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
- 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
- 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
- 2019Self-labelling via simultaneous clustering and representation learningcited by 528
- 2021Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarkscited by 395
- 2021Understanding Dimensional Collapse in Contrastive Self-supervised Learningcited by 378
- 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 326
- 2021The Intrinsic Dimension of Images and Its Impact on Learningcited by 315
- 2020Contrastive Clusteringcited by 265
- 2021Divide and Contrast: Self-supervised Learning from Uncurated Datacited by 85
- 2021Learning Representation for Clustering via Prototype Scattering and Positive Samplingcited by 58
- 2017von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verificationcited by 46
- 2022Learning Where to Learn in Cross-View Self-Supervised Learningcited by 31
- 2023Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learningcited by 18
- 2022SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videoscited by 17
- 2023All4One: Symbiotic Neighbour Contrastive Learning via Self-Attention and Redundancy Reductioncited by 11
- 2021Image Modeling with Deep Convolutional Gaussian Mixture Modelscited by 4
- 2022A new perspective on probabilistic image modelingcited by 2
Built on by
Not cited yet.