Papers › PTQ4SAM: Post-Training Quantization for Segment Anything

PTQ4SAM: Post-Training Quantization for Segment Anything

6 May 2024CVPR 2024 1arXiv:2405.03144archive 2025-07-28

Chengtao Lv, Hong Chen, Jinyang Guo, Yifu Ding, Xianglong Liu

Segment Anything Model (SAM) has achieved impressive performance in many computer vision tasks. However, as a large-scale model, the immense memory and computation costs hinder its practical deployment. In this paper, we propose a post-training quantization (PTQ) framework for Segment Anything Model, namely PTQ4SAM. First, we investigate the inherent bottleneck of SAM quantization attributed to the bimodal distribution in post-Key-Linear activations. We analyze its characteristics from both per-tensor and per-channel perspectives, and propose a Bimodal Integration strategy, which utilizes a mathematically equivalent sign operation to transform the bimodal distribution into a relatively easy-quantized normal distribution offline. Second, SAM encompasses diverse attention mechanisms (i.e., self-attention and two-way cross-attention), resulting in substantial variations in the post-Softmax distributions. Therefore, we introduce an Adaptive Granularity Quantization for Softmax through searching the optimal power-of-two base, which is hardware-friendly. Extensive experimental results across various vision tasks (instance segmentation, semantic segmentation and object detection), datasets and model variants show the superiority of PTQ4SAM. For example, when quantizing SAM-L to 6-bit, we achieve lossless accuracy for instance segmentation, about 0.5% drop with theoretical 3.9× acceleration. The code is available at https://github.com/chengtao-lv/PTQ4SAM.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 8 ran (3 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 8 samples that ran has no recorded date.

chengtao-lv/ptq4sam officialmentioned in papermentioned on GitHubpytorchSyntology: 9 samples, 8 ran (5 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · our draft was wrong
3ran
1unverified

Licence: 9 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from chengtao-lv/ptq4sam. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

chengtao-lv/ptq4sam official repository 9 samples, 8 ran (5 instrument-failed) · 1 unverified
round_ste in 18 papers
census: 3 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
ptq4sam/quantization/util_quant.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 675da8641c602b03 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
fake_logquantize_per_tensor_affine ptq4sam/quantization/util_quant.py ran no licence file found · pointer only · 235ca98c280dc43c · report fixture: signature x:Tensor/2/float, scale:Tensor/0/float, quant_min:int/0/int, quant_max:int/0/int, tau:int/0/int · returned Tensor · level recorded 2026-09-24
fake_quantize_per_tensor_affine ptq4sam/quantization/util_quant.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f5f3045a5c318d7c · report fixture: signature x:Tensor/2/float, scale:float/0/float, zero_point:int/0/int, quant_min:int/0/int, quant_max:int/0/int · returned Tensor · level recorded 2026-09-22
get_module_args ptq4sam/quantization/quantized_module_matmul.py ran · our draft was wrong no licence file found · pointer only · 2f381ebd3e023bfa · report fixture: signature module:callable/0/? · returned dict · level recorded 2026-09-24
lp_loss in 20 papers
census: 6 implementations from 10 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
ptq4sam/solver/recon.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 8003cb7a5176e497 · report fixture: signature pred:Tensor/2/float, tgt:Tensor/2/float, p:float/0/float · returned Tensor · level recorded 2026-09-22
parse_config in 30 papers ptq4sam/solver/utils.py ran · our draft was wrong no licence file found · pointer only · afb8f93395a730c8 · report fixture: signature config_file:str/0/str · returned EasyDict · level recorded 2026-09-24
process_checkpoint in 87 papers mmdetection/.dev_scripts/gather_models.py ran no licence file found · pointer only · 138e112e22b0314e · report fixture: signature in_file:str/0/str, out_file:str/0/str · returned str · level recorded 2026-09-25
update_specialized_quantizer_config ptq4sam/model/quant_model.py ran no licence file found · pointer only · 7a2978318593f764 · report fixture: signature base_config:dict/0/?, quantizer_name:str/0/str · returned dict · level recorded 2026-09-24
ordered_yaml_dump in 33 papers mmdetection/.dev_scripts/gather_models.py unverified no licence file found · pointer only · 8ff99a6bd2ebf598 · report

Tasks

Instance SegmentationObject DetectionQuantizationSegmentationSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SAMSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections