Towards Clip-Free Quantized Super-Resolution Networks: How to Tame Representative Images
Super-resolution (SR) networks have been investigated for a while, with their mobile and lightweight versions gaining noticeable popularity recently. Quantization, the procedure of decreasing the precision of network parameters (mostly FP32 to INT8), is also utilized in SR networks for establishing mobile compatibility. This study focuses on a very important but mostly overlooked post-training quantization (PTQ) step: representative dataset (RD), which adjusts the quantization range for PTQ. We propose a novel pipeline (clip-free quantization pipeline, CFQP) backed up with extensive experimental justifications to cleverly augment RD images by only using outputs of the FP32 model. Using the proposed pipeline for RD, we can successfully eliminate unwanted clipped activation layers, which nearly all mobile SR methods utilize to make the model more robust to PTQ in return for a large overhead in runtime. Removing clipped activations with our method significantly benefits overall increased stability, decreased inference runtime up to 54% on some SR models, better visual quality results compared to INT8 clipped models - and outperforms even some FP32 non-quantized models, both in runtime and visual quality, without the need for retraining with clipped activation.
Code (0)
등록된 구현이 없습니다.
Tasks
QuantizationSuper-ResolutionSimilar Papers 제목 키워드 기반
Analysis of Quantized Models
Weight-quantized networks have small storage and fast inference, but training can still be time-consuming. This can be improved with distributed learning. To reduce the high communication cost due to worker-server synchr…
QuantizationTAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models
Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to imperceptible adversarial perturbations, raising serious safety concerns for o…
Zero-shot GeneralizationAdversarial RobustnessGenerating metamers of human scene understanding
Human vision combines low-resolution "gist" information from the visual periphery with sparse but high-resolution information from fixated locations to construct a coherent understanding of a visual scene. In this paper,…
Scene UnderstandingEfficient INT8 Single-Image Super-Resolution via Deployment-Aware Quantization and Teacher-Guided Training
Efficient single-image super-resolution (SISR) requires balancing reconstruction fidelity, model compactness, and robustness under low-bit deployment, which is especially challenging for x3 SR. We present a deployment-or…
Image Super-ResolutionZero-shot Adaptation of Stable Diffusion via Plug-in Hierarchical Degradation Representation for Real-World Super-Resolution
Real-World Image Super-Resolution (Real-ISR) aims to recover high-quality images from low-quality inputs degraded by unknown and complex real-world factors. Real-world scenarios involve diverse and coupled degradations, …
Image Super-Resolution