Research map / Continual learning / Class-incremental

Hyperbolic Displacement-Constrained Adaptation for CLIP-Based Class-Incremental Learning

NeurIPS 2026 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a hyperbolic displacement-constrained adaptation method for CLIP-based class-incremental learning to reduce catastrophic forgetting during session-wise adaptation.

Problem

Class-incremental learning with CLIP suffers from catastrophic forgetting when the model is adapted across sessions.

Approach

Constrains adaptation via displacement in hyperbolic space, relative to prior-task knowledge; the abstract does not give specifics beyond this framing.

Closest papers by meaning

• Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning (NeurIPS 2026 · similarity 0.89)
• Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning (ICML 2025 · similarity 0.87)
• Bayesian Test-Time Adaptation for Vision-Language Models (CVPR 2025 · similarity 0.87)
• A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models (CVPR 2024 · similarity 0.86)
• Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method (ICML 2024 · similarity 0.86)
• SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning (ICLR 2025 · similarity 0.86)