Patch Knowledge Transfer for Efficient AI-Generated Image Quality Assessment

• URL: http://arxiv.org/abs/2607.05605v1
• Date: Mon, 06 Jul 2026 20:02:25 GMT
• Title: Patch Knowledge Transfer for Efficient AI-Generated Image Quality Assessment
• Abstract summary: Current mainstream approaches exhibit two key limitations.<n>We propose Patch Knowledge Transfer (PKT), a knowledge distillation-based optimization framework.<n>We show that PKT enables the student model to maintain performance comparable to the teacher while reducing computational costs by 67.7%.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rapid advancement of image generation technologies, perceptual quality assessment of AI-generated images has emerged as a crucial research direction in computer vision. The core challenge of this task lies in achieving efficient quality assessment for massive generated images. Current mainstream approaches exhibit two key limitations: 1) Methods employing complex feature extraction strategies, while improving performance, incur prohibitive computational costs that hinder real-time inference; 2) Simple image scaling-based solutions, despite their computational efficiency, demonstrate significantly inferior assessment accuracy. To address this critical issue, we propose Patch Knowledge Transfer (PKT), a knowledge distillation-based optimization framework that achieves synergistic optimization of visual representation capability and inference efficiency through an innovative multi-level knowledge transfer mechanism. Specifically, we design a dual-model architecture: a teacher model with local-global hybrid processing provides high-quality supervision signals, while a student model relying solely on global processing efficiently inherits the teacher's representation capacity through multi-level supervision. Extensive experiments conducted on 4 AIGIQA databases demonstrate that the PKT framework enables the student model to maintain performance comparable to the teacher while reducing computational costs by 67.7\%. Furthermore, compared to existing methods, our approach achieves a superior balance between model efficiency and assessment accuracy.

Related papers

• Implicit Neural Representation-Based Continuous Single Image Super Resolution: An Empirical Study [50.15623093332659]
  Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR)<n>We compare existing techniques across diverse settings and present aggregated performance results on multiple image quality metrics.<n>We examine a new loss function that penalizes intensity variations while preserving edges, textures, and finer details during training.
  arXiv  Detail & Related papers  (2026-01-25T07:09:20Z)
• MSPT: A Lightweight Face Image Quality Assessment Method with Multi-stage Progressive Training [2.4399096457147356]
  We propose a lightweight face quality assessment network with Multi-Stage Progressive Training (MSPT)<n>Our network employs a three-stage progressive training strategy that gradually introduces more diverse data samples.<n>MSPT achieved the second highest score on the VQualA 2025 face image quality assessment benchmark dataset.
  arXiv  Detail & Related papers  (2025-08-11T03:37:09Z)
• ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models [39.520825264698374]
  Vision Transformers (ViTs) have delivered remarkable progress through global self-attention, yet their quadratic complexity can become prohibitive for high-resolution inputs.<n>We present ViT-Linearizer, a cross-architecture distillation framework that transfers rich ViT representations into a linear-time, recurrent-style model.<n>Our results underscore the good potential of RNN-based solutions for large-scale visual tasks, bridging the gap between theoretical efficiency and real-world practice.
  arXiv  Detail & Related papers  (2025-03-30T15:35:24Z)
• CTSR: Controllable Fidelity-Realness Trade-off Distillation for Real-World Image Super Resolution [52.93785843453579]
  Real-world image super-resolution is a critical image processing task, where two key evaluation criteria are the fidelity to the original image and the visual realness of the generated results.<n>We propose a distillation-based approach that leverages the geometric decomposition of both fidelity and realness, alongside the performance advantages of multiple teacher models.<n> Experiments conducted on several real-world image super-resolution benchmarks demonstrate that our method surpasses existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-03-18T14:06:39Z)
• Striving for Faster and Better: A One-Layer Architecture with Auto Re-parameterization for Low-Light Image Enhancement [50.93686436282772]
  We aim to delve into the limits of image enhancers both from visual quality and computational efficiency.<n>By rethinking the task demands, we build an explicit connection, i.e., visual quality and computational efficiency are corresponding to model learning and structure design.<n>Ultimately, this achieves efficient low-light image enhancement using only a single convolutional layer, while maintaining excellent visual quality.
  arXiv  Detail & Related papers  (2025-02-27T08:20:03Z)
• Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models [4.737806982257592]
  This study proposes a knowledge distillation algorithm based on large language models and feature alignment.<n>The proposed model performs very close to the state-of-the-art GPT-4 model in terms of evaluation indicators such as perplexity, BLEU, ROUGE, and CER.
  arXiv  Detail & Related papers  (2024-12-27T04:37:06Z)
• Enhancing Content Representation for AR Image Quality Assessment Using Knowledge Distillation [3.020452010930984]
  This paper presents a deep learning-based objective metric designed specifically for assessing image quality for Augmented Reality scenarios.<n>It entails four key steps, (1) fine-tuning a self-supervised pre-trained vision transformer to extract prominent features from reference images, (2) quantifying distortions by computing shift representations, (3) employing cross-attention-based decoders to capture perceptual quality features, and (4) integrating regularization techniques and label smoothing to address the overfitting problem.
  arXiv  Detail & Related papers  (2024-12-08T17:25:30Z)
• Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark [62.58869921806019]
  We propose a task decomposition evaluation framework based on GPT-4o to automatically construct a new training dataset. We design innovative training strategies to effectively distill GPT-4o's evaluation capabilities into a 7B open-source MLLM, MiniCPM-V-2.6. Experimental results demonstrate that our distilled open-source MLLM significantly outperforms the current state-of-the-art GPT-4o-base baseline.
  arXiv  Detail & Related papers  (2024-11-23T08:06:06Z)
• big.LITTLE Vision Transformer for Efficient Visual Recognition [34.015778625984055]
  big.LITTLE Vision Transformer is an innovative architecture aimed at achieving efficient visual recognition. System is composed of two distinct blocks: the big performance block and the LITTLE efficiency block. When processing an image, our system determines the importance of each token and allocates them accordingly.
  arXiv  Detail & Related papers  (2024-10-14T08:21:00Z)
• Efficient Degradation-aware Any Image Restoration [83.92870105933679]
  We propose textitDaAIR, an efficient All-in-One image restorer employing a Degradation-aware Learner (DaLe) in the low-rank regime. By dynamically allocating model capacity to input degradations, we realize an efficient restorer integrating holistic and specific learning.
  arXiv  Detail & Related papers  (2024-05-24T11:53:27Z)
• Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration [59.6021678234829]
  We propose a novel method to restore the intermediate features for two sparsely sampled and adjacent video frames. With the integration of our method, the efficiency of three commonly used baselines has been improved by over 50%, with a mere 0.5% reduction in recognition accuracy.
  arXiv  Detail & Related papers  (2023-07-27T13:52:42Z)
• Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision [74.9260745577362]
  This paper proposes a unified optimization-inspired learning framework to aggregate Generative, Discriminative, and Corrective (GDC) principles. We construct three propagative modules to effectively solve the optimization models with flexible combinations. Experiments across varied low-level vision tasks validate the efficacy and adaptability of GDC.
  arXiv  Detail & Related papers  (2020-12-10T03:24:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.