Browse State-of-the-Art › Data Free Quantization
Data Free Quantization
16 papers with code · 2 benchmarks · 1 dataset archive 2025-07-28
Data Free Quantization is a technique to achieve a highly accurate quantized model without accessing any training data.
Source: Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| CIFAR-100 (3 rows) | ResNet-20 CIFAR-100 | Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples | code | Syntology official (archive's flag): 1 ran · 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified | Compare |
| CIFAR10 (3 rows) | ResNet-20 CIFAR-10 | Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples | code | Syntology official (archive's flag): 1 ran · 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
1 dataset whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 37 · with a code link: 16 · where Syntology ran a sample: 6 (4 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (6 of 37 tagged: 4 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 37 of 37, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
11 Jun 2019 5 repositories listedThis improves quantization accuracy performance, and can be applied to many common computer vision architectures with a straight forward API call.
-
29 May 2023 3 repositories listed Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)Several post-training quantization methods have been applied to large language models (LLMs), and have been shown to perform well down to 8-bits.
-
7 Mar 2020 3 repositories listedMore critically, our method achieves much higher accuracy on 4-bit quantization than the existing data free quantization method.
-
1 Jan 2020 3 repositories listed Syntology community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 12 unverified (of 19 harvested samples) · 2 pointer-only (licence)Importantly, ZeroQ has a very low computational overhead, and it can finish the entire quantization process in less than 30s (0.
-
4 Nov 2021 2 repositories listed Syntology official (archive's flag): 1 ran · 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)We find that this is often insufficient to capture the distribution of the original data, especially around the decision boundaries.
-
24 May 2025 1 repository listedDiffusion Transformers (DiTs) have emerged as the state-of-the-art architecture for video generation, yet their computational and memory demands hinder practical deployment.
-
16 Dec 2024 1 repository listedThen, in the student training phase, we perform an opposite optimization, which adversarially attempts to reduce the distance of samples of the same classes and enlarge the distance of samples of different classes.
-
24 Sep 2023 1 repository listedInspired by the causal understanding, we propose the Causality-guided Data-free Network Quantization method, Causal-DFQ, to eliminate the reliance on data via approaching an equilibrium of causality-driven intervened…
-
30 May 2023 1 repository listed Syntology official (archive's flag): 3 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 2 pointer-only (licence)On the contrary, we design group-wise quantization functions for activation discretization in different timesteps and sample the optimal timestep for informative calibration image generation, so that our quantized…
-
13 Mar 2023 1 repository listedData-free quantization (DFQ) recovers the performance of quantized network (Q) without the original data, but generates the fake sample via a generator (G) by learning from full-precision network (P), which, however, is…
-
19 Feb 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples)how to generate the samples with desirable adaptability to benefit the quantized network?
-
13 Sep 2022 1 repository listed Syntology official (archive's flag): 4 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified (of 8 harvested samples) · 1 pointer-only (licence)In this paper, we propose PSAQ-ViT V2, a more accurate and general data-free quantization framework for ViTs, built on top of PSAQ-ViT.
-
31 Mar 2022 1 repository listedTo deal with the performance drop induced by quantization errors, a popular method is to use training data to fine-tune quantized networks.
-
4 Mar 2022 1 repository listedThe above insights guide us to design a relative value metric to optimize the Gaussian noise to approximate the real images, which are then utilized to calibrate the quantization parameters.
-
14 Feb 2022 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples) · 2 pointer-only (licence)This paper proposes an on-the-fly DFQ framework with sub-second quantization time, called SQuant, which can quantize networks on inference-only devices with low computation and memory requirements.
-
1 Sep 2021 1 repository listedWe first give a theoretical analysis that the diversity of synthetic samples is crucial for the data-free quantization, while in existing approaches, the synthetic data completely constrained by BN statistics…
-
OuroMamba: A Data-Free Quantization Framework for Vision Mamba Models13 Mar 2025 0 repositories listedWe present OuroMamba, the first data-free post-training quantization (DFQ) method for vision Mamba-based models (VMMs).
-
Enhancing Diversity for Data-free Quantization1 Jan 2025 0 repositories listedModel quantization is an effective way to compress deep neural networks and accelerate the inference time on edge devices.
-
Semantics Prompting Data-Free Quantization for Low-Bit Vision Transformers21 Dec 2024 0 repositories listedData-free quantization (DFQ), which facilitates model quantization without real data to address increasing concerns about data security, has garnered significant attention within the model compression community.
-
A method of using RSVD in residual calculation of LowBit GEMM27 Sep 2024 0 repositories listedThe advancements of hardware technology in recent years has brought many possibilities for low-precision applications.
-
Privacy-Preserving SAM Quantization for Efficient Edge Intelligence in Healthcare14 Sep 2024 0 repositories listedThe disparity in healthcare personnel expertise and medical resources across different regions of the world is a pressing social issue.
-
MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity29 Jul 2024 0 repositories listedData-free quantization (DFQ) is a technique that creates a lightweight network from its full-precision counterpart without the original training data, often through a synthetic dataset.
-
EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs5 Mar 2024 0 repositories listedLarge language models (LLMs) have proven to be very superior to conventional methods in various tasks.
-
Data-Free Quantization via Pseudo-label Filtering1 Jan 2024 0 repositories listedQuantization for model compression can efficiently reduce the network complexity and storage requirement but the original training data is necessary to remedy the performance loss caused by quantization.
-
Robustness-Guided Image Synthesis for Data-Free Quantization5 Oct 2023 0 repositories listedQuantization has emerged as a promising direction for model compression.
-
Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning2 Jul 2023 0 repositories listedNeural network quantization is a very promising solution in the field of model compression, but its resulting accuracy highly depends on a training/fine-tuning process and requires the original data.
-
QNNRepair: Quantized Neural Network Repair23 Jun 2023 0 repositories listedWe present QNNRepair, the first method in the literature for repairing quantized neural networks (QNNs).
-
ACQ: Improving Generative Data-free Quantization Via Attention Correction18 Jan 2023 0 repositories listedData-free quantization aims to achieve model quantization without accessing any authentic sample.
-
Genie: Show Me the Data for Quantization9 Dec 2022 0 repositories listedWe also propose a post-training quantization algorithm to enhance the performance of quantized models.
-
Zero-Shot Learning of a Conditional Generative Adversarial Network for Data-Free Network Quantization26 Oct 2022 0 repositories listedWe propose a novel method for training a conditional generative adversarial network (CGAN) without the use of training data, called zero-shot learning of a CGAN (ZS-CGAN).
-
Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization30 Apr 2022 0 repositories listed
-
Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization8 Apr 2022 0 repositories listed
-
SPIQ: Data-Free Per-Channel Static Input Quantization28 Mar 2022 0 repositories listed
-
29 Mar 2021 0 repositories listed
-
Diversifying Sample Generation for Accurate Data-Free Quantization1 Mar 2021 0 repositories listed
-
Generative Zero-shot Network Quantization21 Jan 2021 0 repositories listed
-
Towards Accurate Quantization and Pruning via Data-free Knowledge Transfer14 Oct 2020 0 repositories listed
Syntology lines on 7 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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