Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization

In this paper, we propose a novel unsupervised clustering approach exploiting the hidden information that is indirectly introduced through a pseudo classification objective. Specifically, we randomly assign a pseudo parent-class label to each observation which is then modified by applying the domain specific transformation associated with the assigned label... (read more)

PDF Abstract ICLR 2018 PDF ICLR 2018 Abstract
No code implementations yet. Submit your code now

Datasets


Results from the Paper


 Ranked #1 on Unsupervised Image Classification on SVHN (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Unsupervised Image Classification MNIST ACOL + GAR + k-means Accuracy 98.32 # 2
Unsupervised Image Classification SVHN ACOL-GAR Acc 76.80 # 1
# of clusters (k) 10 # 1

Methods used in the Paper


METHOD TYPE
Softmax
Output Functions