Associative Deep Clustering: Training a Classification Network with No Labels

132 citations recorded by the source corpus.

How researchers see this paper

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

Invariant Information Clustering for Unsupervised Image Classification and Segmentation (2018, methodology): “However, it is not the same as merely minimising representation distance, as done for example in methods based on k-means [7, 23]: the presence of entropy within I allows us to avoid degeneracy, as discussed in detail below.”
Stacked Capsule Autoencoders (2019, methodology): “In agreement with previous work on unsupervised clustering (Ji et al., 2018; Hu et al., 2017; Hjelm et al., 2019; Haeusser et al., 2018), we train our models and report results on full datasets (TRAIN, VALID and TEST splits).”
Contrastive Clustering (2021, methodology): “We evaluate the proposed CC on six challenging image benchmarks and compare it with 17 representative stateof-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 [3”
Semi-Supervised and Unsupervised Deep Visual Learning: A Survey (2022, methodology): “In online clustering, the cluster assignment step and network training step are coupled in an end-to-end training framework, as represented by IIC [157], AssociativeCluster [158], PICA [149], and SwAV [134].”