← Search

Chiranjeev Chiranjeev

2 accepted papers

2025

Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres

ICML 2025poster

Do contemporary diffusion models preserve the class geometry of hyperspherical data? Standard diffusion models rely on isotropic Gaussian noise in the forward process, inherently favoring Euclidean spaces. However, many real-world problems involve non-Euclidean distributions, such as hyperspherical…

Cited by 0SourcePDFScholar
2024

HyperSpaceX: Radial and Angular Exploration of HyperSpherical Dimensions

ECCV 2024poster

"Traditional deep learning models rely on methods such as softmax cross-entropy and ArcFace loss for tasks like classification and face recognition. These methods mainly explore angular features in a hyperspherical space, often resulting in entangled inter-class features due to dense angular data ac…