Deep Adaptive Image Clustering

By Jianlong Chang, Lingfeng Wang, Gaofeng Meng, Shiming Xiang, Chunhong Pan. 2017

553 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Representation & Self-Supervised Learning

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

In Media Technology

In Representation & Self-Supervised Learning

Citations in the corpus

Learning deep representations by mutual information estimation and maximization (2018, methodology): “Other approaches include deep volume-preserving maps (Dinh et al., 2014, 2016), deep clustering (Xie et al., 2016; Chang et al., 2017), noise as targets (NAT, Bojanowski & Joulin, 2017), self-supervised methods (Doersch & Zisserman, 2017), and co-learning (Dosovitskiy et al., 2016; Sajjadi et al.,…”
Invariant Information Clustering for Unsupervised Image Classification and Segmentation (2018, methodology): “DAC [8], JULE [50], DeepCluster [7], ADC [23] and DEC [49] rely on the inherent visual consistency and disentangling properties [22] of CNNs to produce cluster assignments, which are processed and reinforced in each iteration.”
Prototypical Contrastive Learning of Unsupervised Representations (2020, background): “Approaches in [14, 15, 16, 17, 18, 19] jointly learn image embeddings and cluster assignments, but they have not shown the ability to learn transferable representations from a large scale of images.”
Automatically Discovering and Learning New Visual Categories with Ranking Statistics (2020, unknown): “(2016); Chang et al. (2017); Dizaji et al.”
Contrastive Clustering (2021, methodology): “Both the training and test set are used for CIFAR-10, CIFAR-100 [22], and STL-10 [8], while only the training set is used for ImageNet-10, ImageNet-Dogs [5], and Tiny-ImageNet [23].”
Learning to Discover Novel Visual Categories via Deep Transfer Clustering (2019, background): “Recently, there have been more and more works on clustering in the deep learning literature (e.g., [6, 12, 38, 39, 40]).”
Towards Better Interpretability in Deep Q-Networks (2018, methodology): “…we train fully using backpropagation), works on combining deep embeddings with unsupervised clustering methods (Xie, Girshick, and Farhadi 2016; Chang et al. 2017) (joint optimization/iterative refinement) have started to pick up pace and show better performance compared to traditional…”
Learning To Classify Images Without Labels (2020, methodology): “DEC [52], DAC [6], DeepCluster [4], DeeperCluster [5], or others [1,17,54]) leverage the architecture of CNNs as a prior to cluster images.”
Invariant Information Distillation for Unsupervised Image Segmentation and Clustering (2018, methodology): “We compare against Chang et al. [2017] (DAC), Isola et al. [2015] (Co-Occurence Network or CON), Xie et al. [2016] (DEC), Doersch et al.”
OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in an Open World (2020, methodology): “Inspired by DAC [3] and DCCM [26], we argue that the relation of pairwise images is binary.”
DATA: Differentiable ArchiTecture Approximation With Distribution Guided Sampling (2020, methodology): “Following [72], all architectures are trainedwith learning rate 0.”
Neighborhood Contrastive Learning for Novel Class Discovery (2021, methodology): “The deep learning based methods can be roughly categorized into two kinds where the first kind exploits pairwise similarity of the samples to generate pseudo-labels for clustering [6, 12, 24].”
Deep Comprehensive Correlation Mining for Image Clustering (2019, methodology): “For the loss function lg , there are many choices, such as the contrastive Siamese net loss [5, 32] regularizing the distance between two samples, and the binary cross-entropy loss [8] regularizing the similarity.”
Recognition From Web Data: A Progressive Filtering Approach (2018, unknown): “[32] use Deep Adaptive Clustering to calculate the similarities of pairwise images based on the feature from a CNN, sample similar images, and then train the CNN by using the selected samples to improve the representation performance.”
Semi-Supervised and Unsupervised Deep Visual Learning: A Survey (2022, methodology): “In offline clustering, unsupervised training is alternated between a cluster assignment step and a network training step [139], [140], [170], [171], [182], [191], [192], [193].”
Adaptive Graph Encoder for Attributed Graph Embedding (2020, methodology): “Given the smoothed node features, we further develop a simple node representation learning module based on adaptive learning [6].”
A Survey of Clustering With Deep Learning: From the Perspective of Network Architecture (2018, background): “DAC converges when all instances are used for training and the objective can not be improved further.”