AI Paper Atlas

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

HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding

jiha jang, Hayeon Kim, Junghun James Kim, Chulwon Lee, Se Young Chun

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: CLIP training recipes and data curation · 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 entailment loss L_ent (ablation)HyFL-CLIP · Average of all retrieval benchmarksretrieval accuracy: 69.3 -> 69.8Improved
add cross-manifold distillation L_distill (ablation)HyFL-CLIP · Average of all retrieval benchmarksretrieval accuracy: 68.3 -> 69.3Improved
add L_distill (short-caption retrieval) (ablation)HyFL-CLIP ViT-L/14 · COCO I2TTop-1: 42.77 -> 41.56Improved
add L_ent to improve perturbation robustness (ablation)HyFL-CLIP · Long-caption retrieval under perturbationperformance degradation (%): 35.64 -> 32.38Improved
add L_distill for perturbation robustness (ablation)HyFL-CLIP · Long-caption retrieval under perturbationperformance degradation (%): 32.28 -> 32.38No clear effect
use hyperbolic distance instead of Euclidean for ranking perturbed captionsHyFL-CLIP vs HiMo-CLIP · Perturbed caption rankingmean rank: 184.94 -> 156.99Improved
rank by hyperbolic entailment instead of hyperbolic distance (ablation)HyFL-CLIP · Perturbed caption rankingmean rank: 156.99 -> 78.50Improved
hyperbolic fine-tuning vs HiMo-CLIP under word dropoutHyFL-CLIP · Long-caption retrieval, word dropout p=0.5Top-1 accuracy: 58.75 -> 70.20Improved
hyperbolic fine-tuning vs HiMo-CLIP on Urban-1k ViT-B/16HyFL-CLIP · Urban-1kI2T Top-1: 89.20 -> 91.80Improved
hyperbolic fine-tuning vs HiMo-CLIP on DOCCI ViT-L/14 I2THyFL-CLIP · DOCCII2T Top-1: 82.35 -> 82.12No clear effect
vary lambda1 from 0.01 to 0.20 (ablation)HyFL-CLIP · Retrieval (I2T/T2I)accuracy: 74.58/75.35 -> 75.35/75.75No clear effect
hyperbolic fine-tuning vs HiMo-CLIP on short COCO I2THyFL-CLIP · COCOI2T: 60.84 -> 58.20Hurt

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