paper-with-me

홈 › Papers

The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric

2026-07-20 · Sheng-Yu Wang, Yotam Nitzan, Aaron Hertzmann, Jun-Yan Zhu, Eli Shechtman, Alexei A. Efros, Richard Zhang arxiv

Human visual similarity judgments are context-dependent. For example, two images may be similar in shape but distinct in color. Existing perceptual similarity metrics, however, collapse these nuances into a single scalar value, offering no mechanism to condition on specific aspects. To bridge this gap, we introduce a large-scale dataset of human similarity judgments over image triplets, where each triplet is annotated across multiple, free-form semantic aspects of similarity. Benchmarking a broad range of frontier vision-language models (VLMs) reveals a considerable performance gap compared to human annotators' consensus. Leveraging our data, we fine-tune a VLM to produce our Text-Prompted Image Perceptual Similarity (TPIPS) metric, capturing multiple senses of visual similarity depending on the specified text prompt. We demonstrate that TPIPS aligns more closely with human perception and generalizes reliably beyond the training distribution. Finally, we show that TPIPS unlocks new capabilities in text-guided retrieval, compositional search, and the fine-grained evaluation of generative models. Our code, data, and trained models are at https://peterwang512.github.io/TPIPS

📄 PDF Abstract BibTeX arXiv:2607.18237

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Sense Discovery via Co-Clustering on Images and Text

2015-06-01 · CVPR 2015 6 · Xinlei Chen, Alan Ritter, Abhinav Gupta, Tom Mitchell

We present a co-clustering framework that can be used to discover multiple semantic and visual senses of a given Noun Phrase (NP). Unlike traditional clustering approaches which assume a one-to-one mapping between the cl…

Clustering

A Quadratic 0-1 Programming Approach for Word Sense Disambiguation

2022-01-13 · Boliang Lin

Word Sense Disambiguation (WSD) is the task to determine the sense of an ambiguous word in a given context. Previous approaches for WSD have focused on supervised and knowledge-based methods, but inter-sense interactions…

Combinatorial OptimizationWord Sense DisambiguationWord Similarity

Visualising WordNet Embeddings: some preliminary results

2019-07-01 · GWC 2019 7 · Csaba Veres

AutoExtend is a method for learning unambiguous vector embeddings for word senses. We visualise these word embeddings with t-SNE, which further compresses the vectors to the x,y plane. We show that the t-SNE co-ordinates…

Semantic SimilaritySemantic Textual SimilarityWord Embeddings

PolyUCOMP-CORE\_TYPED: Computing Semantic Textual Similarity using Overlapped Senses

2013-06-01 · SEMEVAL 2013 6 · Jian Xu, Qin Lu
Natural Language InferenceSemantic Textual SimilarityText Summarization

BERT Has Uncommon Sense: Similarity Ranking for Word Sense BERTology

2021-09-20 · EMNLP (BlackboxNLP) 2021 11 · Luke Gessler, Nathan Schneider

An important question concerning contextualized word embedding (CWE) models like BERT is how well they can represent different word senses, especially those in the long tail of uncommon senses. Rather than build a WSD sy…

Retrieval