AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

HyperCLIP++: Fine-Tuning CLIP for Open-Vocabulary Semantic Segmentation in Hyperbolic Space

Zelin Peng, Zhengqin Xu, Changsong Wen, Yu Huang, Yaoming Wang, Xiaokang Yang, Wei Shen

TPAMI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 0 citations (OpenAlex)

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
add Mobius matrix multiplication (ablation)HyperCLIP++ · A-847mIoU: 12.0 -> 13.1Improved
add Mobius matrix multiplication (ablation)HyperCLIP++ · PC-459mIoU: 18.9 -> 20.3Improved
add dual cross-relation communication (DCRC) (ablation)HyperCLIP++ · A-847mIoU: 12.3 -> 13.1Improved
add dual cross-relation communication (DCRC) (ablation)HyperCLIP++ · PC-459mIoU: 19.2 -> 20.3Improved
use DCRC instead of cross-modality only communication (ablation)HyperCLIP++ · A-847mIoU: 12.9 -> 13.1Improved
use DCRC instead of cross-layer only communication (ablation)HyperCLIP++ · A-847mIoU: 12.5 -> 13.1Improved
use DCRC instead of cross-attention adapter (ablation)HyperCLIP++ · A-847mIoU: 12.7 -> 13.1Improved
fine-tune both encoders instead of image encoder only (ablation)HyperCLIP++ w/o DCRC · A-847mIoU: 10.3 -> 12.3Improved
fine-tune both encoders instead of text encoder only (ablation)HyperCLIP++ w/o DCRC · A-847mIoU: 11.1 -> 12.3Improved
hyperbolic fine-tuning instead of Euclidean LoRA (ablation)HyperCLIP++ · A-847mIoU: 11.4 -> 13.1Improved
increase diagonal block size n from 1 to 128 (ablation)HyperCLIP++ · A-847mIoU: 6.0 -> 13.1Improved
increase diagonal block size n from 128 to 256 (ablation)HyperCLIP++ · A-847mIoU: 13.1 -> 13.0No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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