SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.04006 · CVPR · 2025

DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation

Amin Karimi

arXiv · PDF · Open in the Atlas

Code that ran

1 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 7 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2503.04006.json · badge: /api/ran/2503.04006.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
aminpdik/DSV-LFS community
Papers with Code archive
1 ran · 7 no recorded run
FunctionStatusWhere it lives
CenterPivotConv4d Ran
ran on a synthesized input · constructed an object; no result was computed
aminpdik/DSV-LFS/model/DSVLFS.py
pointer only (licence: NONE) · get_code("5626200667c7acd2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminpdik/DSV-LFS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

DSVLFSMetaModel Not yet run
unverified (harvested, no recorded run)
aminpdik/DSV-LFS/model/DSVLFS.py
pointer only (licence: NONE) · get_code("e757783a56fe4bac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminpdik/DSV-LFS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

DSVLFSModel Not yet run
unverified (harvested, no recorded run)
aminpdik/DSV-LFS/model/DSVLFS.py
pointer only (licence: NONE) · get_code("7418550c1ed630cd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminpdik/DSV-LFS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

LlavaLlamaModel Not yet run
unverified (harvested, no recorded run)
aminpdik/DSV-LFS/model/DSVLFS.py
pointer only (licence: NONE) · get_code("8874bfc77c28b08a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminpdik/DSV-LFS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

LlavaMetaModel Not yet run
unverified (harvested, no recorded run)
aminpdik/DSV-LFS/model/DSVLFS.py
pointer only (licence: NONE) · get_code("ce5bf617752572ad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminpdik/DSV-LFS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

_build_sam Not yet run
unverified (harvested, no recorded run)
aminpdik/DSV-LFS/model/DSVLFS.py
pointer only (licence: NONE) · get_code("788bbfaef0618316")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminpdik/DSV-LFS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

build_sam_vit_h Not yet run
unverified (harvested, no recorded run)
aminpdik/DSV-LFS/model/DSVLFS.py
pointer only (licence: NONE) · get_code("814491f8751ca732")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminpdik/DSV-LFS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

build_vision_tower Not yet run
unverified (harvested, no recorded run)
aminpdik/DSV-LFS/model/DSVLFS.py
pointer only (licence: NONE) · get_code("f553b519cf8e68ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aminpdik/DSV-LFS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 4 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
build_sam_vit_h
brick of this paper's assembly: helper
37 other papers
34 dated earlier, 3 later · 2 only as an assembly brick
2304.06790 (2023-04)
Inpaint Anything: Segment Anything Meets Image Inpainting
2304.12306 (2023-04)
Segment Anything in Medical Images
2305.01586 (2023-05)
An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems
and 34 more not named here
LlavaLlamaModel
brick of this paper's assembly: helper
13 other papers
7 dated earlier, 5 later, 1 same year, order not determinable · 3 only as an assembly brick
2304.08485 (2023-04)
Visual Instruction Tuning
2404.05673 (2024-04)
CoReS: Orchestrating the Dance of Reasoning and Segmentation
2405.14974 (2024-05)
LOVA 3 : Learning to Visual Question Answering, Asking and Assessment
and 10 more not named here
build_vision_tower
brick of this paper's assembly: helper
4 other papers
3 dated earlier, 1 later · 2 only as an assembly brick
2304.08485 (2023-04)
Visual Instruction Tuning
2406.20095 (2024-06)
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
2502.13508 (2025-02)
VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation
and 1 more not named here
_build_sam
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later · 2 only as an assembly brick
2404.05673 (2024-04)
CoReS: Orchestrating the Dance of Reasoning and Segmentation
2603.20193 (2026-03)
From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Few-shot semantic segmentation (FSS) aims to enable models to segment novel/unseen object classes using only a limited number of labeled examples. However, current FSS methods frequently struggle with generalization due to incomplete and biased feature representations, especially when support images do not capture the full appearance variability of the target class. To improve the FSS pipeline, we propose a novel framework that utilizes large language models (LLMs) to adapt general class semantic information to the query image. Furthermore, the framework employs dense pixel-wise matching to identify similarities between query and support images, resulting in enhanced FSS performance. Inspired by reasoning-based segmentation frameworks, our method, named DSV-LFS, introduces an additional token into the LLM vocabulary, allowing a multimodal LLM to generate a "semantic prompt" from class descriptions. In parallel, a dense matching module identifies visual similarities between the query and support images, generating a "visual prompt". These prompts are then jointly employed to guide the prompt-based decoder for accurate segmentation of the query image. Comprehensive experiments on the benchmark datasets Pascal-5 i and COCO-20 i demonstrate that our framework achieves state-ofthe-art performance-by a significant margin-demonstrating superior generalization to novel classes and robustness across diverse scenarios. The source code is available at https://github.com/aminpdik/DSV-LFS

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2503.04006")
get_code_for_paper("2503.04006")
have("2503.04006")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2503.04006.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2503.04006.svg)](https://syntology.ai/paper/2503.04006)

Connect an agent — have() is free.