SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.01567 · NeurIPS · 2023

Segment Anything in High Quality

Martin Danelljan, Hkust, Yu-Wing Tai, Chi-Keung Tang, Lei Ke, Fisher Yu, Yifan Liu, Mingqiao Ye

arXiv · PDF · Open in the Atlas

Code that ran

3 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 14 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2306.01567.json · badge: /api/ran/2306.01567.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
SysCV/SAM-HQ canonical (classifier label)
classifier basis: census
3 ran · 10 no recorded run
syscv/sam-hq canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
sqhuang0103/samreg community
Papers with Code archive
0 ran · 3 no recorded run
FunctionStatusWhere it lives
compute_axial_cis Ran
ran, violated the contract we drafted
SysCV/SAM-HQ/sam-hq2/sam2/modeling/position_encoding.py
code served (permissive licence) · get_code("7ceaad42da42edd5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (12, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    "dim": 8,
    "end_x": 4,
    "end_y": 3,
    "theta": 10000.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (12, 4) — shape (12, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
init_t_xy Ran
ran, honoured the contract we drafted
SysCV/SAM-HQ/sam-hq2/sam2/modeling/position_encoding.py
code served (permissive licence) · get_code("bb060d29525f90eb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    'end_x': 4,
    'end_y': 3,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
reshape_for_broadcast Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SysCV/SAM-HQ/sam-hq2/sam2/modeling/position_encoding.py
code served (permissive licence) · get_code("f8f09f78b474ee7c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (1, 3, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects:
# - freqs_cis: a 2D tensor with shape (x.shape[-2], x.shape[-1])
# - x: a tensor with ndim >= 2

# Let's create x with shape (batch, seq_len, hidden_dim) = (2, 3, 4)
# This means x.shape[-2] = 3 and x.shape[-1] = 4
x = torch.randn(2, 3, 4)

# freqs_cis should have shape (3, 4) to match (x.shape[-2], x.shape[-1])
freqs_cis = torch.randn(3, 4)

ARGS = {
    "freqs_cis": freqs_cis,
    "x": x,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (1, 3, 4) — shape (1, 3, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ImageEncoderViT Not yet run
unverified (harvested, no recorded run)
sqhuang0103/samreg/model/segment_anything/modeling/sam.py
pointer only (licence: NONE) · get_code("c5057a50b489acc7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sqhuang0103/samreg 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.

MaskDecoder Not yet run
unverified (harvested, no recorded run)
sqhuang0103/samreg/model/segment_anything/modeling/sam.py
pointer only (licence: NONE) · get_code("34833c5f5b063e06")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sqhuang0103/samreg 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.

MaskDecoderHQ Not yet run
unverified (harvested, no recorded run)
syscv/sam-hq/segment_anything/modeling/mask_decoder_hq.py
code served (permissive licence) · get_code("365b6e55c7dfeb2a")
How it ran

no invocation recorded.

Sam Not yet run
unverified (harvested, no recorded run)
sqhuang0103/samreg/model/segment_anything/modeling/sam.py
pointer only (licence: NONE) · get_code("7ee31020ecfc08df")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sqhuang0103/samreg 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_sam2 Not yet run
unverified (harvested, no recorded run)
SysCV/SAM-HQ/sam-hq2/sam2/build_sam.py
code served (permissive licence) · get_code("f9850c1d4acdbb5a")
How it ran

no invocation recorded.

build_sam2_hq_video_predictor Not yet run
unverified (harvested, no recorded run)
SysCV/SAM-HQ/sam-hq2/sam2/build_sam.py
code served (permissive licence) · get_code("71ae361c498f6c02")
How it ran

no invocation recorded.

build_sam2_video_predictor Not yet run
unverified (harvested, no recorded run)
SysCV/SAM-HQ/sam-hq2/sam2/build_sam.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from jovanavidenovic/dam4sam, is pointer only (licence: NONE) · get_code("c1b9e144954a57e5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from jovanavidenovic/dam4sam, and GitHub detected no licence in that repository 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_b Not yet run
unverified (harvested, no recorded run)
SysCV/SAM-HQ/segment_anything/build_sam_baseline.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yatengLG/ISAT_with_segment_anything, is pointer only (licence: NOASSERTION) · get_code("f9bc5f31ce61cee8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yatengLG/ISAT_with_segment_anything, and GitHub could not classify the licence of that repository (NOASSERTION). 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_b Not yet run
unverified (harvested, no recorded run)
SysCV/SAM-HQ/segment_anything/build_sam.py
code served (permissive licence) · get_code("ce435ccfda4628ae")
How it ran

no invocation recorded.

build_sam_vit_h Not yet run
unverified (harvested, no recorded run)
SysCV/SAM-HQ/segment_anything/build_sam_baseline.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yatengLG/ISAT_with_segment_anything, is pointer only (licence: NOASSERTION) · get_code("6b77c1f11fff3ed6")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yatengLG/ISAT_with_segment_anything, and GitHub could not classify the licence of that repository (NOASSERTION). 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)
SysCV/SAM-HQ/segment_anything/build_sam.py
code served (permissive licence) · get_code("28898b68c1790b24")
How it ran

no invocation recorded.

build_sam_vit_l Not yet run
unverified (harvested, no recorded run)
SysCV/SAM-HQ/segment_anything/build_sam_baseline.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yatengLG/ISAT_with_segment_anything, is pointer only (licence: NOASSERTION) · get_code("3f8890e695469246")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yatengLG/ISAT_with_segment_anything, and GitHub could not classify the licence of that repository (NOASSERTION). 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_l Not yet run
unverified (harvested, no recorded run)
SysCV/SAM-HQ/segment_anything/build_sam.py
code served (permissive licence) · get_code("c11d78a854b4aa23")
How it ran

no invocation recorded.

register_tiny_vit_model Not yet run
unverified (harvested, no recorded run)
SysCV/SAM-HQ/segment_anything/modeling/tiny_vit_sam.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from KHU-AGI/BUS, is pointer only (licence: NONE) · get_code("9d5a5692e595b123")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from KHU-AGI/BUS, and GitHub detected no licence in that repository 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 11 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 3 the same month, 11 later) and 3 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 37 other papers
3 dated earlier, 2 the same month, 32 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
build_sam_vit_b 34 other papers
3 dated earlier, 2 the same month, 29 later
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 31 more not named here
build_sam_vit_l 34 other papers
3 dated earlier, 2 the same month, 29 later
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 31 more not named here
compute_axial_cis 13 other papers
1 dated earlier, 12 later
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2408.00874 (2024-08)
Medical SAM 2: Segment medical images as video via Segment Anything Model 2
2408.02635 (2024-08)
Interactive 3D Medical Image Segmentation with SAM 2
and 10 more not named here
init_t_xy 13 other papers
1 dated earlier, 12 later
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2408.00874 (2024-08)
Medical SAM 2: Segment medical images as video via Segment Anything Model 2
2408.02635 (2024-08)
Interactive 3D Medical Image Segmentation with SAM 2
and 10 more not named here
reshape_for_broadcast 13 other papers
1 dated earlier, 12 later
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2408.00874 (2024-08)
Medical SAM 2: Segment medical images as video via Segment Anything Model 2
2408.02635 (2024-08)
Interactive 3D Medical Image Segmentation with SAM 2
and 10 more not named here
build_sam2 10 other papers
1 dated earlier, 9 later
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2408.07931 (2024-08)
Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning
2410.16268 (2024-10)
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
and 7 more not named here
build_sam2_video_predictor 5 other papers
5 later
2408.07931 (2024-08)
Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning
2410.16268 (2024-10)
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
2411.17576 (2024-11)
A Distractor-Aware Memory for Visual Object Tracking with SAM2
and 2 more not named here
register_tiny_vit_model 3 other papers
3 later
2312.09579 (2023-12)
MobileSAMv2: Faster Segment Anything to Everything
2312.13789 (2023-12)
TinySAM: Pushing the Envelope for Efficient Segment Anything Model
2405.19899 (2024-05)
Open-Set Domain Adaptation for Semantic Segmentation
ImageEncoderViT
brick of this paper's assembly: model
2 other papers
2 later
2405.19783 (2024-05)
Instruction-Guided Visual Masking
2503.16997 (2025-03)
Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation
Sam
brick of this paper's assembly: entry
1 other paper
1 later
2401.08083 (2024-01)
UV-SAM: Adapting Segment Anything Model for Urban Village Identification

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

The recent Segment Anything Model (SAM) represents a big leap in scaling up segmentation models, allowing for powerful zero-shot capabilities and flexible prompting. Despite being trained with 1.1 billion masks, SAM's mask prediction quality falls short in many cases, particularly when dealing with objects that have intricate structures. We propose HQ-SAM, equipping SAM with the ability to accurately segment any object, while maintaining SAM's original promptable design, efficiency, and zero-shot generalizability. Our careful design reuses and preserves the pre-trained model weights of SAM, while only introducing minimal additional parameters and computation. We design a learnable High-Quality Output Token, which is injected into SAM's mask decoder and is responsible for predicting the high-quality mask. Instead of only applying it on mask-decoder features, we first fuse them with early and final ViT features for improved mask details. To train our introduced learnable parameters, we compose a dataset of 44K fine-grained masks from several sources. HQ-SAM is only trained on the introduced detaset of 44k masks, which takes only 4 hours on 8 GPUs. We show the efficacy of HQ-SAM in a suite of 10 diverse segmentation datasets across different downstream tasks, where 8 out of them are evaluated in a zero-shot transfer protocol. Our code and pretrained models are at https://github.com/SysCV/SAM-HQ.

For agents

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

get_harvested_code_for_paper("2306.01567")
get_code_for_paper("2306.01567")
have("2306.01567")

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

curl https://syntology.ai/api/ran/2306.01567.json

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

[![Syntology run record](https://syntology.ai/api/ran/2306.01567.svg)](https://syntology.ai/paper/2306.01567)

Connect an agent — have() is free.