Work

Paint: Accurate, efficient, and sparse Model Inversion via peripheral sparsification and anchor alignment

Year: 2026
Type: article
Abstract: How can we reconstruct training data from a pre-trained model without access to the original dataset? Model Inversion (MI) attempts to synthesize samples similar to the training dataset. This capability is particularly useful in data-free applications, such as data-free quantization and data-free knowledge transfer, where synthetic data replace inaccessible training samples. For these applications, MI needs to generate high-fidelity samples to preserve semantic information while remaining computationally efficient, enabling scalable generation for reliable downstream performance. However, existing MI methods fail to achieve both high fidelity and efficiency simultaneously. In this paper, we propose Paint (Peripheral sparsification and Anchor-aligned INversion Technique), an accurate, efficient, and sparse MI framework for generating high-fidelity synthetic data. Paint integrates low-pass filtering during inversion to suppress high-frequency noise, aligns salient regions toward anchor with peripheral sparsification to preserve object structures during sparse inversion, and exploits soft targets to better capture the predictive uncertainty. Extensive experiments demonstrate that Paint improves inversion efficiency for ViTs and achieves accuracy gains of up to 5.33%p in data-free scenarios.
Source: PLoS ONE
Language: English
Open Access status: gold
Estimated APC paid: $2,382
OpenAlex ID: W7234903317
FWCI:
Cites: 22
Cited by:
Related to: 10
Parts: 15