paper-with-me

홈 › Papers

Probing CLIP's Comprehension of 360-Degree Textual and Visual Semantics

2026-04-27 · Hai Wang, Xiaochen Yang, Mingzhi Dong, Jing-Hao Xue arxiv

The dream of instantly creating rich 360-degree panoramic worlds from text is rapidly becoming a reality, yet a crucial gap exists in our ability to reliably evaluate their semantic alignment. Contrastive Language-Image Pre-training (CLIP) models, standard AI evaluators, predominantly trained on perspective image-text pairs, face an open question regarding their understanding of the unique characteristics of 360-degree panoramic image-text pairs. This paper addresses this gap by first introducing two concepts: \emph{360-degree textual semantics}, semantic information conveyed by explicit format identifiers, and \emph{360-degree visual semantics}, invariant semantics under horizontal circular shifts. To probe CLIP's comprehension of these semantics, we then propose novel evaluation methodologies using keyword manipulation and horizontal circular shifts of varying magnitudes. Rigorous statistical analyses across popular CLIP configurations reveal that: (1) CLIP models effectively leverage explicit textual identifiers, demonstrating an understanding of 360-degree textual semantics; and (2) CLIP models fail to robustly preserve semantic alignment under horizontal circular shifts, indicating limited comprehension of 360-degree visual semantics. To address this limitation, we propose a LoRA-based fine-tuning framework that explicitly instills invariance to circular shifts. Our fine-tuned models exhibit improved comprehension of 360-degree visual semantics, though with a slight degradation in original semantic evaluation performance, highlighting a fundamental trade-off in adapting CLIP to 360-degree panoramic images. Code is available at https://github.com/littlewhitesea/360Semantics.

📄 PDF Abstract BibTeX arXiv:2604.24642

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections

2024-11-28 · Mohamed Fazli Imam, Rufael Fedaku Marew, Jameel Hassan, Mustansar Fiaz 외

In the era of foundation models, CLIP has emerged as a powerful tool for aligning text and visual modalities into a common embedding space. However, the alignment objective used to train CLIP often results in subpar visu…

image-classificationImage ClassificationSelf-Supervised Learningzero-shot-classification+1

The Solution for the 5th GCAIAC Zero-shot Referring Expression Comprehension Challenge

2024-07-06 · Longfei Huang, Feng Yu, Zhihao Guan, Zhonghua Wan 외

This report presents a solution for the zero-shot referring expression comprehension task. Visual-language multimodal base models (such as CLIP, SAM) have gained significant attention in recent years as a cornerstone of …

Referring ExpressionReferring Expression Comprehension

DisCLIP: Open-Vocabulary Referring Expression Generation

2023-05-30 · Lior Bracha, Eitan Shaar, Aviv Shamsian, Ethan Fetaya 외

Referring Expressions Generation (REG) aims to produce textual descriptions that unambiguously identifies specific objects within a visual scene. Traditionally, this has been achieved through supervised learning methods,…

Referring ExpressionReferring expression generation

Learning to Decompose Visual Features with Latent Textual Prompts

2022-10-09 · Feng Wang, Manling Li, Xudong Lin, Hairong Lv 외

Recent advances in pre-training vision-language models like CLIP have shown great potential in learning transferable visual representations. Nonetheless, for downstream inference, CLIP-like models suffer from either 1) d…

Retrieval

Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignment

2025-09-23 · Tong Zhang, Kuofeng Gao, Jiawang Bai, Leo Yu Zhang 외 arxiv

Recent studies have shown that Contrastive Language-Image Pre-training (CLIP) models are threatened by targeted data poisoning and backdoor attacks due to massive training image-caption pairs crawled from the Internet. P…