# CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Data

arXiv: https://arxiv.org/abs/1705.07091 · HTML: https://mlsanity.com/paper/1705.07091/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2017.

## Built on by (most cited first, 16 of 16)

- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions](https://mlsanity.com/paper/2206.07579/) (2022)
- [Effective Neural Topic Modeling with Embedding Clustering Regularization](https://mlsanity.com/paper/2306.04217/) (2023)
- [Novel Class Discovery: an Introduction and Key Concepts](https://mlsanity.com/paper/2302.12028/) (2023)
- [Deep Attention-guided Graph Clustering with Dual Self-supervision](https://mlsanity.com/paper/2111.05548/) (2021)
- [Dense Video Captioning Using Unsupervised Semantic Information](https://mlsanity.com/paper/2112.08455/) (2021)
- [Scene-Aware Feature Matching](https://mlsanity.com/paper/2308.09949/) (2023)
- [Mixture-of-Experts Variational Autoencoder for Clustering and Generating from Similarity-Based Representations on Single Cell Data](https://mlsanity.com/paper/1910.07763/) (2019)
- [DeepCluE: Enhanced Image Clustering via Multi-layer Ensembles in Deep Neural Networks](https://mlsanity.com/paper/2206.00359/) (2022)
- [ClusVPR: Efficient Visual Place Recognition with Clustering-based Weighted Transformer](https://mlsanity.com/paper/2310.04099/) (2023)
- [Bootstrap Deep Spectral Clustering with Optimal Transport](https://mlsanity.com/paper/2508.04200/) (2025)
- [Learning to Structure an Image with Few Colors and Beyond](https://mlsanity.com/paper/2208.08438/) (2022)
- [DMS: Differentiable Mean Shift for Dataset Agnostic Task Specific Clustering Using Side Information](https://mlsanity.com/paper/2305.18492/) (2023)
- [fMBN-E: Efficient Unsupervised Network Structure Ensemble and Selection for Clustering](https://mlsanity.com/paper/2107.02071/) (2021)
- [Clustering based on Mixtures of Sparse Gaussian Processes](https://mlsanity.com/paper/2303.13665/) (2023)
- [Historical Printed Ornaments: Dataset and Tasks](https://mlsanity.com/paper/2408.08633/) (2024)

## Abstract (arXiv)

Given a large unlabeled set of images, how to efficiently and effectively group them into clusters based on extracted visual representations remains a challenging problem. To address this problem, we propose a convolutional neural network (CNN) to jointly solve clustering and representation learning in an iterative manner. In the proposed method, given an input image set, we first randomly pick k samples and extract their features as initial cluster centroids using the proposed CNN with an initial model pre-trained from the ImageNet dataset. Mini-batch k-means is then performed to assign cluster labels to individual input samples for a mini-batch of images randomly sampled from the input image set until all images are processed. Subsequently, the proposed CNN simultaneously updates the parameters of the proposed CNN and the centroids of image clusters iteratively based on stochastic gradient descent. We also proposed a feature drift compensation scheme to mitigate the drift error caused by feature mismatch in representation learning. Experimental results demonstrate the proposed method outperforms start-of-the-art clustering schemes in terms of accuracy and storage complexity on large-scale image sets containing millions of images.