LLaFS++ : Few-Shot Image Segmentation With Large Language Models

Despite the rapid advancements in few-shot segmentation (FSS), most of existing methods in this domain are hampered by their reliance on the limited and biased information from only a small number of labeled samples. This limitation inherently restricts their capability to achieve sufficiently high...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 47(2025), 9 vom: 26. Aug., Seite 7715-7732
1. Verfasser: Zhu, Lanyun (VerfasserIn)
Weitere Verfasser: Chen, Tianrun, Ji, Deyi, Xu, Peng, Ye, Jieping, Liu, Jun
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM389036293
003 DE-627
005 20250807232043.0
007 cr uuu---uuuuu
008 250714s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2025.3573609  |2 doi 
028 5 2 |a pubmed25n1523.xml 
035 |a (DE-627)NLM389036293 
035 |a (NLM)40418603 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Zhu, Lanyun  |e verfasserin  |4 aut 
245 1 0 |a LLaFS++  |b Few-Shot Image Segmentation With Large Language Models 
264 1 |c 2025 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 07.08.2025 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Despite the rapid advancements in few-shot segmentation (FSS), most of existing methods in this domain are hampered by their reliance on the limited and biased information from only a small number of labeled samples. This limitation inherently restricts their capability to achieve sufficiently high levels of performance. To address this issue, this paper proposes a pioneering framework named LLaFS++, which, for the first time, applies large language models (LLMs) into FSS and achieves notable success. LLaFS++ leverages the extensive prior knowledge embedded by LLMs to guide the segmentation process, effectively compensating for the limited information contained in the few-shot labeled samples and thereby achieving superior results. To enhance the effectiveness of the text-based LLMs in FSS scenarios, we present several innovative and task-specific designs within the LLaFS++ framework. Specifically, we introduce an input instruction that allows the LLM to directly produce segmentation results represented as polygons, and propose a region-attribute corresponding table to simulate the human visual system and provide multi-modal guidance. We also synthesize pseudo samples and use curriculum learning for pretraining to augment data and achieve better optimization, and propose a novel inference method to mitigate potential oversegmentation hallucinations caused by the regional guidance information. Incorporating these designs, LLaFS++ constitutes an effective framework that achieves state-of-the-art results on multiple datasets including PASCAL-$5^{i}$5i, COCO-$20^{i}$20i, and FSS-1000. Our superior performance showcases the remarkable potential of applying LLMs to process few-shot vision tasks 
650 4 |a Journal Article 
700 1 |a Chen, Tianrun  |e verfasserin  |4 aut 
700 1 |a Ji, Deyi  |e verfasserin  |4 aut 
700 1 |a Xu, Peng  |e verfasserin  |4 aut 
700 1 |a Ye, Jieping  |e verfasserin  |4 aut 
700 1 |a Liu, Jun  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 47(2025), 9 vom: 26. Aug., Seite 7715-7732  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:47  |g year:2025  |g number:9  |g day:26  |g month:08  |g pages:7715-7732 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2025.3573609  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 47  |j 2025  |e 9  |b 26  |c 08  |h 7715-7732