Converge to Surprise: Evolutionary Self-supervised Image Clustering

• URL: http://arxiv.org/abs/2607.06887v1
• Date: Wed, 08 Jul 2026 01:09:21 GMT
• Title: Converge to Surprise: Evolutionary Self-supervised Image Clustering
• Abstract summary: We propose a self-supervised framework for image clustering.<n>Our framework achieves new state-of-the-art results in non-parametric self-supervised image clustering.
• Score: 1.6686955491488271
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most self-supervised image clustering models, actually almost all deep learning approaches, are based on gradient descent: In order to calculate the loss, every optimization step requires a clearly defined target, whether a contrastive split, a masked patch or entity, an EMA-teacher output, a pseudo-label, or a differentiable information-theoretic functional. We propose a self-supervised framework that drops this requirement for image clustering. Without any prior knowledge, we have to assume that each pixel is i.i.d. according to the Principle of Maximum Entropy. Taking this as our null hypothesis H0, we define a "surprise score" that measures how unlikely the model's output representation would be under H0. Maximizing the surprise score forces the deep learning model to reject H0 - equivalently, to discover non-random feature from data. Also, here is our fundamental assumption: a surprise score cannot, in general, be reduced to a per-step loss. Hence, we propose the "converge-to-surprise" scheme to optimize our model: an evolution-strategy (ES) outer loop, which directly maximizes the surprise score without needing its gradient, paired with a periodic gradient-descent inner loop, which uses the surprising clusters already discovered by ES as surrogate targets. On standard image benchmarks, our framework achieves new state-of-the-art results in non-parametric self-supervised image clustering - the strictest deep-clustering setting, in which the number of ground-truth classes is not given to the model.

Related papers

• Where Does Generative Difficulty Reside? An Empirical Study of Target Representations [62.54876287800644]
  The target representation defines the distribution an image generator must learn, yet it is often treated as an interchangeable interface.<n>We study raw pixels, SD-VAE latents and DINOv2 as well as MAE representation-autoencoder features within a unified masked autoregressive rectified-flow model.<n>Our results show that compression, reconstruction fidelity, token dimensionality, and visible semantic clustering do not individually predict generative behavior.
  arXiv  Detail & Related papers  (2026-08-01T12:32:31Z)
• Self-Enhanced Image Clustering with Cross-Modal Semantic Consistency [57.961869351897384]
  We propose a framework based on cross-modal semantic consistency for efficient image clustering.<n>Our framework first builds a strong foundation via Cross-Modal Semantic Consistency.<n>In the first stage, we train lightweight clustering heads to align with the rich semantics of the pre-trained model.<n>In the second stage, we introduce a Self-Enhanced fine-tuning strategy.
  arXiv  Detail & Related papers  (2025-08-02T08:12:57Z)
• Few-shot Algorithm Assurance [11.924406021826606]
  deep learning models are vulnerable to image distortion.<n>Model Assurance under Image Distortion is a classification task.<n>We propose a novel Conditional Level Set Estimation algorithm.
  arXiv  Detail & Related papers  (2024-12-28T21:11:55Z)
• Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection [58.87142367781417]
  A naively trained detector tends to favor overfitting to the limited and monotonous fake patterns, causing the feature space to become highly constrained and low-ranked.<n>One potential remedy is incorporating the pre-trained knowledge within the vision foundation models to expand the feature space.<n>By freezing the principal components and adapting only the remained components, we preserve the pre-trained knowledge while learning fake patterns.
  arXiv  Detail & Related papers  (2024-11-23T19:10:32Z)
• Self-Supervised Dataset Distillation for Transfer Learning [77.4714995131992]
  We propose a novel problem of distilling an unlabeled dataset into a set of small synthetic samples for efficient self-supervised learning (SSL) We first prove that a gradient of synthetic samples with respect to a SSL objective in naive bilevel optimization is textitbiased due to randomness originating from data augmentations or masking. We empirically validate the effectiveness of our method on various applications involving transfer learning.
  arXiv  Detail & Related papers  (2023-10-10T10:48:52Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching [63.88319217738223]
  We present Matcher, a novel perception paradigm that utilizes off-the-shelf vision foundation models to address various perception tasks. Matcher demonstrates impressive generalization performance across various segmentation tasks, all without training. Our results further showcase the open-world generality and flexibility of Matcher when applied to images in the wild.
  arXiv  Detail & Related papers  (2023-05-22T17:59:43Z)
• Semi-Supervised Clustering of Sparse Graphs: Crossing the Information-Theoretic Threshold [3.6052935394000234]
  Block model is a canonical random graph model for clustering and community detection on network-structured data. No estimator based on the network topology can perform substantially better than chance on sparse graphs if the model parameter is below a certain threshold. We prove that with an arbitrary fraction of the labels feasible throughout the parameter domain.
  arXiv  Detail & Related papers  (2022-05-24T00:03:25Z)
• Clustering by Maximizing Mutual Information Across Views [62.21716612888669]
  We propose a novel framework for image clustering that incorporates joint representation learning and clustering. Our method significantly outperforms state-of-the-art single-stage clustering methods across a variety of image datasets.
  arXiv  Detail & Related papers  (2021-07-24T15:36:49Z)
• Learning Hierarchical Graph Neural Networks for Image Clustering [81.5841862489509]
  We propose a hierarchical graph neural network (GNN) model that learns how to cluster a set of images into an unknown number of identities. Our hierarchical GNN uses a novel approach to merge connected components predicted at each level of the hierarchy to form a new graph at the next level.
  arXiv  Detail & Related papers  (2021-07-03T01:28:42Z)
• Self-Supervised Classification Network [3.8073142980733]
  Self-supervised end-to-end classification neural network learns labels and representations simultaneously. First unsupervised end-to-end classification network to perform well on the large-scale ImageNet dataset.
  arXiv  Detail & Related papers  (2021-03-19T19:29:42Z)
• Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation [49.90178055521207]
  This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths. In particular, we devise a graph neural network (GNN) for group-wise semantic mining, wherein input images are represented as graph nodes.
  arXiv  Detail & Related papers  (2020-12-09T12:40:13Z)
• GATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering [9.722607434532883]
  We propose a self-supervised clustering network for image Clustering (GATCluster) Rather than extracting intermediate features first and then performing the traditional clustering, GATCluster semantic cluster labels without further post-processing. We develop a two-step learning algorithm that is memory-efficient for clustering large-size images.
  arXiv  Detail & Related papers  (2020-02-27T00:57:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.