Saved in:
Bibliographic Details
Main Authors: Yang, Tinghan, Rahman, Md Ashiqur, Yeh, Raymond A.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.14197
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909744388636672
author Yang, Tinghan
Rahman, Md Ashiqur
Yeh, Raymond A.
author_facet Yang, Tinghan
Rahman, Md Ashiqur
Yeh, Raymond A.
contents Symmetry is one of the most fundamental geometric cues in computer vision, and detecting it has been an ongoing challenge. With the recent advances in vision-language models,~i.e., CLIP, we investigate whether a pre-trained CLIP model can aid symmetry detection by leveraging the additional symmetry cues found in the natural image descriptions. We propose CLIPSym, which leverages CLIP's image and language encoders and a rotation-equivariant decoder based on a hybrid of Transformer and $G$-Convolution to detect rotation and reflection symmetries. To fully utilize CLIP's language encoder, we have developed a novel prompting technique called Semantic-Aware Prompt Grouping (SAPG), which aggregates a diverse set of frequent object-based prompts to better integrate the semantic cues for symmetry detection. Empirically, we show that CLIPSym outperforms the current state-of-the-art on three standard symmetry detection datasets (DENDI, SDRW, and LDRS). Finally, we conduct detailed ablations verifying the benefits of CLIP's pre-training, the proposed equivariant decoder, and the SAPG technique. The code is available at https://github.com/timyoung2333/CLIPSym.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14197
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CLIPSym: Delving into Symmetry Detection with CLIP
Yang, Tinghan
Rahman, Md Ashiqur
Yeh, Raymond A.
Computer Vision and Pattern Recognition
Symmetry is one of the most fundamental geometric cues in computer vision, and detecting it has been an ongoing challenge. With the recent advances in vision-language models,~i.e., CLIP, we investigate whether a pre-trained CLIP model can aid symmetry detection by leveraging the additional symmetry cues found in the natural image descriptions. We propose CLIPSym, which leverages CLIP's image and language encoders and a rotation-equivariant decoder based on a hybrid of Transformer and $G$-Convolution to detect rotation and reflection symmetries. To fully utilize CLIP's language encoder, we have developed a novel prompting technique called Semantic-Aware Prompt Grouping (SAPG), which aggregates a diverse set of frequent object-based prompts to better integrate the semantic cues for symmetry detection. Empirically, we show that CLIPSym outperforms the current state-of-the-art on three standard symmetry detection datasets (DENDI, SDRW, and LDRS). Finally, we conduct detailed ablations verifying the benefits of CLIP's pre-training, the proposed equivariant decoder, and the SAPG technique. The code is available at https://github.com/timyoung2333/CLIPSym.
title CLIPSym: Delving into Symmetry Detection with CLIP
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.14197