Can Modern Vision Models Understand the Difference Between an Object and a Look-alike?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cohen, Itay, Fetaya, Ethan, Rosenfeld, Amir
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914169753698304
author Cohen, Itay
Fetaya, Ethan
Rosenfeld, Amir
author_facet Cohen, Itay
Fetaya, Ethan
Rosenfeld, Amir
contents Recent advances in computer vision have yielded models with strong performance on recognition benchmarks; however, significant gaps remain in comparison to human perception. One subtle ability is to judge whether an image looks like a given object without being an instance of that object. We study whether vision-language models such as CLIP capture this distinction. We curated a dataset named RoLA (Real or Lookalike) of real and lookalike exemplars (e.g., toys, statues, drawings, pareidolia) across multiple categories, and first evaluate a prompt-based baseline with paired "real"/"lookalike" prompts. We then estimate a direction in CLIP's embedding space that moves representations between real and lookalike. Applying this direction to image and text embeddings improves discrimination in cross-modal retrieval on Conceptual12M, and also enhances captions produced by a CLIP prefix captioner.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19200
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can Modern Vision Models Understand the Difference Between an Object and a Look-alike?
Cohen, Itay
Fetaya, Ethan
Rosenfeld, Amir
Computer Vision and Pattern Recognition
Recent advances in computer vision have yielded models with strong performance on recognition benchmarks; however, significant gaps remain in comparison to human perception. One subtle ability is to judge whether an image looks like a given object without being an instance of that object. We study whether vision-language models such as CLIP capture this distinction. We curated a dataset named RoLA (Real or Lookalike) of real and lookalike exemplars (e.g., toys, statues, drawings, pareidolia) across multiple categories, and first evaluate a prompt-based baseline with paired "real"/"lookalike" prompts. We then estimate a direction in CLIP's embedding space that moves representations between real and lookalike. Applying this direction to image and text embeddings improves discrimination in cross-modal retrieval on Conceptual12M, and also enhances captions produced by a CLIP prefix captioner.
title Can Modern Vision Models Understand the Difference Between an Object and a Look-alike?
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.19200