Robust Estimation Techniques

Meer, Peter

doi:10.1007/978-3-030-03243-2_882-1

Cited by 2 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Robustness (Box 1979) is defined as the property of a procedure that renders the answers it gives insensitivity to departures, which is used to describe systems, models, or images. Image robustness (Meer 2004;Vacavant 2016) is a concept in signal processing that means the image still has a certain degree of fidelity after various signal processing or attacks. In the field of watermarking, a group of methods design robust watermarks to resist the transformations of images (Cox et al 1996).…”

Section: Image Robustnessmentioning

confidence: 99%

Robustness-Guided Image Synthesis for Data-Free Quantization

Bai,

Yang,

Chu

et al. 2024

AAAI

View full text Add to dashboard Cite

Quantization has emerged as a promising direction for model compression. Recently, data-free quantization has been widely studied as a promising method to avoid privacy concerns, which synthesizes images as an alternative to real training data. Existing methods use classification loss to ensure the reliability of the synthesized images. Unfortunately, even if these images are well-classified by the pre-trained model, they still suffer from low semantics and homogenization issues. Intuitively, these low-semantic images are sensitive to perturbations, and the pre-trained model tends to have inconsistent output when the generator synthesizes an image with low semantics. To this end, we propose Robustness-Guided Image Synthesis (RIS), a simple but effective method to enrich the semantics of synthetic images and improve image diversity, further boosting the performance of data-free compression tasks. Concretely, we first introduce perturbations on input and model weight, then define the inconsistency metrics at feature and prediction levels before and after perturbations. On the basis of inconsistency on two levels, we design a robustness optimization objective to eliminate low-semantic images. Moreover, we also make our approach diversity-aware by forcing the generator to synthesize images with small correlations. With RIS, we achieve state-of-the-art performance for various settings on data-free quantization and can be extended to other data-free compression tasks.

show abstract