Unsupervised Learning of Human Pose Distance Metric via Sparsity Locality Preserving Projections

Wang, Shaofan; Xin, Yongjia; Kong, Dehui; Yin, Baocai

doi:10.1109/tmm.2018.2859029

Cited by 7 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although such deliberation is necessary for obtaining the competitive clustering performance, it is harmful to choosing a suitable architecture for a given task. It makes state-of-the-art deep clustering architectures become increasingly domain-specific [22]- [24], [50]. In addition, after being optimized in the first stage, the learned representation is fixed, so it cannot be further improved to obtain better performance in the clustering stage.…”

Section: Related Workmentioning

confidence: 99%

Learning the Precise Feature for Cluster Assignment

Gan

Dong

Zhou

et al. 2022

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Clustering is one of the fundamental tasks in computer vision and pattern recognition. Recently, deep clustering methods (algorithms based on deep learning) have attracted wide attention with their impressive performance. Most of these algorithms combine deep unsupervised representation learning and standard clustering together. However, the separation of representation learning and clustering will lead to suboptimal solutions because the two-stage strategy prevents representation learning from adapting to subsequent tasks (e.g., clustering according to specific cues). To overcome this issue, efforts have been made in the dynamic adaption of representation and cluster assignment, whereas current state-of-the-art methods suffer from heuristically constructed objectives with representation and cluster assignment alternatively optimized. To further standardize the clustering problem, we audaciously formulate the objective of clustering as finding a precise feature as the cue for cluster assignment. Based on this, we propose a general-purpose deep clustering framework which radically integrates representation learning and clustering into a single pipeline for the first time. The proposed framework exploits the powerful ability of recently developed generative models for learning intrinsic features, and imposes an entropy minimization on the distribution of the cluster assignment by a dedicated variational algorithm. Experimental results show that the performance of the proposed method is superior, or at least comparable to, the state-of-the-art methods on the handwritten digit recognition, fashion recognition, face recognition and object recognition benchmark datasets.

show abstract

Section: Related Workmentioning

confidence: 99%