# Revisiting Vision Language Foundations for No-Reference Image Quality Assessment

arXiv: https://arxiv.org/abs/2509.17374 · HTML: https://mlsanity.com/paper/2509.17374/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Image editing and quality assessment, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 9 of its 44 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Image editing and quality assessment](https://mlsanity.com/mllm/image-editing-and-quality-assessment/)

## Builds on (most cited first, 9 of 9)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [Searching for Activation Functions](https://mlsanity.com/paper/1710.05941/) (2017)
- [Mish: A Self Regularized Non-Monotonic Activation Function](https://mlsanity.com/paper/1908.08681/) (2019)
- [DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning](https://mlsanity.com/paper/2001.08113/) (2020)
- [DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild](https://mlsanity.com/paper/2405.19996/) (2024)
- [Regularization and Reparameterization Avoid Vanishing Gradients in Sigmoid-Type Networks](https://mlsanity.com/paper/2106.02260/) (2021)
- [Image and Video Quality Assessment using Prompt-Guided Latent Diffusion Models for Cross-Dataset Generalization](https://mlsanity.com/paper/2406.04654/) (2024)

## Built on by (most cited first, 1 of 1)

- [Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI](https://mlsanity.com/paper/2608.05258/) (2026)

## Abstract (arXiv)

Large-scale vision language pre-training has recently shown promise for no-reference image-quality assessment (NR-IQA), yet the relative merits of modern Vision Transformer foundations remain poorly understood. In this work, we present the first systematic evaluation of six prominent pretrained backbones, CLIP, SigLIP2, DINOv2, DINOv3, Perception, and ResNet, for the task of No-Reference Image Quality Assessment (NR-IQA), each finetuned using an identical lightweight MLP head. Our study uncovers two previously overlooked factors: (1) SigLIP2 consistently achieves strong performance; and (2) the choice of activation function plays a surprisingly crucial role, particularly for enhancing the generalization ability of image quality assessment models. Notably, we find that simple sigmoid activations outperform commonly used ReLU and GELU on several benchmarks. Motivated by this finding, we introduce a learnable activation selection mechanism that adaptively determines the nonlinearity for each channel, eliminating the need for manual activation design, and achieving new state-of-the-art SRCC on CLIVE, KADID10K, and AGIQA3K. Extensive ablations confirm the benefits across architectures and regimes, establishing strong, resource-efficient NR-IQA baselines.