Anisotropic Agglomerative Adaptive Mean-Shift
This is an incremental improvement for practitioners in clustering and mode detection, addressing specific bottlenecks in Mean Shift applications.
The paper tackles the limitations of Mean Shift clustering due to isotropic and homoscedastic assumptions by introducing an adaptive method with unsupervised local bandwidth selection, resulting in better detail preservation and clustering salience in low-dimensional spaces.
Mean Shift today, is widely used for mode detection and clustering. The technique though, is challenged in practice due to assumptions of isotropicity and homoscedasticity. We present an adaptive Mean Shift methodology that allows for full anisotropic clustering, through unsupervised local bandwidth selection. The bandwidth matrices evolve naturally, adapting locally through agglomeration, and in turn guiding further agglomeration. The online methodology is practical and effecive for low-dimensional feature spaces, preserving better detail and clustering salience. Additionally, conventional Mean Shift either critically depends on a per instance choice of bandwidth, or relies on offline methods which are inflexible and/or again data instance specific. The presented approach, due to its adaptive design, also alleviates this issue - with a default form performing generally well. The methodology though, allows for effective tuning of results.