The reviewed record of science sign in
Pith

arxiv: 2412.03561 · v1 · pith:YQPJVUXC · submitted 2024-12-04 · cs.CV · cs.AI

FLAIR: VLM with Fine-grained Language-informed Image Representations

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:YQPJVUXCrecord.jsonopen to challenge →

classification cs.CV cs.AI
keywords imagefine-grainedflairrepresentationsdetailedabilityclipcontent
0
0 comments X
read the original abstract

CLIP has shown impressive results in aligning images and texts at scale. However, its ability to capture detailed visual features remains limited because CLIP matches images and texts at a global level. To address this issue, we propose FLAIR, Fine-grained Language-informed Image Representations, an approach that utilizes long and detailed image descriptions to learn localized image embeddings. By sampling diverse sub-captions that describe fine-grained details about an image, we train our vision-language model to produce not only global embeddings but also text-specific image representations. Our model introduces text-conditioned attention pooling on top of local image tokens to produce fine-grained image representations that excel at retrieving detailed image content. We achieve state-of-the-art performance on both, existing multimodal retrieval benchmarks, as well as, our newly introduced fine-grained retrieval task which evaluates vision-language models' ability to retrieve partial image content. Furthermore, our experiments demonstrate the effectiveness of FLAIR trained on 30M image-text pairs in capturing fine-grained visual information, including zero-shot semantic segmentation, outperforming models trained on billions of pairs. Code is available at https://github.com/ExplainableML/flair .

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Reviving In-domain Fine-tuning Methods for Source-Free Cross-domain Few-shot Learning

    cs.CV 2026-05 unverdicted novelty 7.0

    LoRA adapters fix collapsed visual CLS token attention in CLIP for superior cross-domain few-shot learning, and the new Semantic Probe framework revives prompt methods to reach state-of-the-art on four benchmarks.