# CLIP-Guided Label-Free Discriminative Region Scoring for Fine-Grained Classification

arXiv: https://arxiv.org/abs/2607.13437 · HTML: https://mlsanity.com/paper/2607.13437/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 15 Jul 2026.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena](https://mlsanity.com/paper/2112.07566/) (2021)
- [Part-based R-CNNs for Fine-grained Category Detection](https://mlsanity.com/paper/1407.3867/) (2014)
- [Learning to Navigate for Fine-grained Classification](https://mlsanity.com/paper/1809.00287/) (2018)
- [Fine-graind Image Classification via Combining Vision and Language](https://mlsanity.com/paper/1704.02792/) (2017)
- [Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models](https://mlsanity.com/paper/2406.02915/) (2024)
- [Diversified Visual Attention Networks for Fine-Grained Object Classification](https://mlsanity.com/paper/1606.08572/) (2016)
- [Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation](https://mlsanity.com/paper/2404.06362/) (2024)
- [Fine-grained Visual Classification with High-temperature Refinement and Background Suppression](https://mlsanity.com/paper/2303.06442/) (2023)
- [Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score](https://mlsanity.com/paper/2507.09615/) (2025)

## Abstract (arXiv)

Recent vision models such as CLIP and SAM enable training-free segmentation and semantic encoding for fine-grained classification. A common approach is to compare the representations of segmented image regions with the text prompt embeddings of the corresponding labels. However, it remains unclear how different local regions and CLIP-based scoring strategies affect the selection of discriminative evidence, especially when ground-truth labels are unavailable. In this paper, we propose a unified CLIP-guided label-free region scoring framework for fine-grained classification. The framework evaluates cosine similarity-based, margin-based, and entropy-based scoring strategies using both SAM-generated masks and random crops, and introduces two label-free pseudo-label variants based on global image embeddings and local region embeddings. We conduct experiments on five fine-grained classification datasets to systematically compare different region generation methods and scoring strategies. The results show that Soft Negative Margin scoring achieves the strongest performance, and pseudo-label scoring closely approximates true-label performance. Although SAM produces semantically meaningful masks, random-crop-based pseudo-label scoring consistently outperforms SAM-based scoring across all datasets, suggesting that random crops preserve surrounding information and provide more stable semantic context when pseudo-labels are noisy. In addition, SAM masks benefit from aggregating embeddings from all regions, whereas random crops tend to perform better with a smaller top-k subset. These findings provide new insights for fine-grained classification.