Deep Comprehensive Correlation Mining for Image Clustering

By Jianlong Wu, Keyu Long, Fei Wang, Chen Qian, Cheng Li, Zhouchen Lin, Hongyuan Zha. 2019

196 citations recorded by the source corpus.

Recent developed deep unsupervised methods allow us to jointly learn representation and cluster unlabelled data. These deep clustering methods %like DAC start with mainly focus on the correlation among samples, e.g., selecting high precision pairs to gradually tune the feature representation, which neglects other useful correlations. In this paper, we propose a novel clustering framework, named deep comprehensive correlation mining~(DCCM), for exploring and taking full advantage of various kinds of correlations behind the unlabeled data from three aspects: 1) Instead of only using pair-wise information, pseudo-label supervision is proposed to investigate category information and learn discriminative features. 2) The features' robustness to image transformation of input space is fully explored, which benefits the network learning and significantly improves the performance. 3) The triplet mutual information among features is presented for clustering problem to lift the recently discovered instance-level deep mutual information to a triplet-level formation, which further helps to learn more discriminative features. Extensive experiments on several challenging datasets show that our method achieves good performance, e.g., attaining 62.3% clustering accuracy on CIFAR-10, which is 10.1% higher than the state-of-the-art results.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Jianlong Wu
2. Fei Wang
3. Chen Qian
4. Zhouchen Lin
5. Changshui Zhang
6. Yue Liao
7. Hongyuan Zha
8. Xiaojie Li

In Media Technology

1. Joey Tianyi Zhou
2. Shan You
3. Peng Hu
4. Xi Peng
5. Hongyuan Zha
6. Changshui Zhang
7. Fei Wang
8. Dezhong Peng

Citations in the corpus

• GreedyNAS: Towards Fast One-Shot NAS With Greedy Supernet (2020, background): “By dint of automatic feature engineering, deep neural networks (DNNs) have achieved remarkable success in various computer vision tasks, such as image classification [37, 36, 41, 33, 32, 15, 39], visual generation [34, 35], image retrieval [40, 7, 8, 12] and semantic comprehension [18, 17].”
• Local Correlation Consistency for Knowledge Distillation (2020, background): “Correlation learning [30] receives much attention for KD recently.”
• Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space (2020, background): “Recently, deploying deep neural networks on edge devices has appealed much attention due to their achieved success in various tasks [32, 19, 36, 34, 13, 35, 33, 15, 38].”
• Essential Tensor Learning for Multi-View Spectral Clustering (2018, methodology): “During the past decades, a variety of methods [1]–[9] for clustering have been proposed.”
• CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection (2020, background): “With the development of deep learning, object detection has achieved great progress [10, 9, 30, 27, 25, 21, 11, 22, 1, 17, 34, 33, 36, 20, 19, 16, 39].”
• Contrastive Clustering (2021, background): “…six challenging image benchmarks and compare it with 17 representative state-of-the-art clustering approaches, including k-means [27], SC [37], AC [11], NMF [2], AE [1], DAE [32], DCGAN [29], DeCNN [36], VAE [21], JULE [35], DEC [34], DAC [6], ADC [16], DDC [4], DCCM [33], IIC [20] and PICA [19].”