AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

Hyperbolic Prototype Learning with Uncertainty-Aware Consistency for Continual Test-Time Segmentation

Siddhant Gole, Akash Pal, Amit More, S Divakar Bhat, Subhasis Chaudhuri, Biplab Banerjee

CVPR 2026 · Continual learning › Domain and prompt-based · approach: Continual test-time adaptation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use hyperbolic (Poincare ball) space instead of Euclidean for prototype segmentation (ablation)HyperProtoSeg · Cityscapes (source val)mIoU: 78.07 -> 79.96Improved
use hyperbolic geometry to reduce error accumulation over 10 CTTA rounds (ablation)HyperProtoSeg · Cityscapes->ACDCmIoU degradation round 1 to 10: -1.46 -> -0.62Improved
add prototypical framework to Euclidean SegFormer (ablation)Euclidean SegFormer · Cityscapes (source val)mIoU: 76.74 -> 78.07Improved
add regularizer Lreg on Euclidean feature norms (ablation)HyperProtoSeg · IDD (source val)mIoU: 70.17 -> 72.29Improved
add prototype separation loss Lsep (ablation)HyperProtoSeg · IDD (source val)mIoU: 72.29 -> 74.34Improved
use consistency-based uncertainty instead of MC dropout (ablation)HBCA · IDD->IDD-AW CTTAmIoU: 52.78 -> 57.12Improved
use consistency-based uncertainty instead of hyperbolic norm (ablation)HBCA · IDD->IDD-AW CTTAmIoU: 53.27 -> 57.12Improved
add directional boundary loss on uncertain pixels (ablation)HBCA · IDD->IDD-AW CTTAmIoU: 56.24 -> 57.12Improved
apply geodesic distance minimization (Lcore) on uncertain pixels (ablation)HBCA · IDD->IDD-AW CTTAmIoU: 56.24 -> 56.01Hurt
apply geodesic distance minimization (Lcore) on uncertain pixels (ablation)HBCA · Cityscapes->ACDC CTTAmIoU: 56.34 -> 55.82Hurt
HBCA vs best prior CTTA (Hybrid TTA) on IDD->IDD-AWHBCA · IDD->IDD-AW CTTAmean mIoU: 54.91 -> 57.12Improved
entropy minimization (TENT) as CTTA methodHyperProtoSeg source model · IDD->IDD-AW CTTAmean mIoU: 51.31 -> 51.45No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy