Cross-Dataset-Robust Method for Blind Real-World Image Quality
Assessment
- URL: http://arxiv.org/abs/2309.14868v1
- Date: Tue, 26 Sep 2023 11:57:12 GMT
- Title: Cross-Dataset-Robust Method for Blind Real-World Image Quality
Assessment
- Authors: Yuan Chen, Zhiliang Ma and Yang Zhao
- Abstract summary: A robust blind image quality assessment (BIQA) method is designed based on three aspects, i.e., robust training strategy, large-scale real-world dataset, and powerful backbone.
A large-scale real-world image dataset with 1,000,000 image pairs and pseudo-labels is then proposed for training the final cross-dataset-robust model.
- Score: 13.00611103494356
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Although many effective models and real-world datasets have been presented
for blind image quality assessment (BIQA), recent BIQA models usually tend to
fit specific training set. Hence, it is still difficult to accurately and
robustly measure the visual quality of an arbitrary real-world image. In this
paper, a robust BIQA method, is designed based on three aspects, i.e., robust
training strategy, large-scale real-world dataset, and powerful backbone.
First, many individual models based on popular and state-of-the-art (SOTA)
Swin-Transformer (SwinT) are trained on different real-world BIQA datasets
respectively. Then, these biased SwinT-based models are jointly used to
generate pseudo-labels, which adopts the probability of relative quality of two
random images instead of fixed quality score. A large-scale real-world image
dataset with 1,000,000 image pairs and pseudo-labels is then proposed for
training the final cross-dataset-robust model. Experimental results on
cross-dataset tests show that the performance of the proposed method is even
better than some SOTA methods that are directly trained on these datasets, thus
verifying the robustness and generalization of our method.
Related papers
- A Large-scale AI-generated Image Inpainting Benchmark [11.216906046169683]
We propose a methodology for creating high-quality inpainting datasets and apply it to create DiQuID.
DiQuID comprises over 95,000 inpainted images generated from 78,000 original images sourced from MS-COCO, RAISE, and OpenImages.
We provide comprehensive benchmarking results using state-of-the-art forgery detection methods, demonstrating the dataset's effectiveness in evaluating and improving detection algorithms.
arXiv Detail & Related papers (2025-02-10T15:56:28Z) - Swin Transformer for Robust Differentiation of Real and Synthetic Images: Intra- and Inter-Dataset Analysis [0.0]
This study proposes a Swin Transformer-based model for accurate differentiation between natural and synthetic images.
The model's performance was evaluated through intra-dataset and inter-dataset testing across three distinct datasets.
arXiv Detail & Related papers (2024-09-07T06:43:17Z) - Q-Ground: Image Quality Grounding with Large Multi-modality Models [61.72022069880346]
We introduce Q-Ground, the first framework aimed at tackling fine-scale visual quality grounding.
Q-Ground combines large multi-modality models with detailed visual quality analysis.
Central to our contribution is the introduction of the QGround-100K dataset.
arXiv Detail & Related papers (2024-07-24T06:42:46Z) - Opinion-Unaware Blind Image Quality Assessment using Multi-Scale Deep Feature Statistics [54.08757792080732]
We propose integrating deep features from pre-trained visual models with a statistical analysis model to achieve opinion-unaware BIQA (OU-BIQA)
Our proposed model exhibits superior consistency with human visual perception compared to state-of-the-art BIQA models.
arXiv Detail & Related papers (2024-05-29T06:09:34Z) - Consistency Regularization for Generalizable Source-free Domain
Adaptation [62.654883736925456]
Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset.
Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets.
We propose a consistency regularization framework to develop a more generalizable SFDA method.
arXiv Detail & Related papers (2023-08-03T07:45:53Z) - Effective Robustness against Natural Distribution Shifts for Models with
Different Training Data [113.21868839569]
"Effective robustness" measures the extra out-of-distribution robustness beyond what can be predicted from the in-distribution (ID) performance.
We propose a new evaluation metric to evaluate and compare the effective robustness of models trained on different data.
arXiv Detail & Related papers (2023-02-02T19:28:41Z) - Learning from Mixed Datasets: A Monotonic Image Quality Assessment Model [17.19991754976893]
We propose a monotonic neural network for IQA model learning with different datasets combined.
In particular, our model consists of a dataset-shared quality regressor and several dataset-specific quality transformers.
arXiv Detail & Related papers (2022-09-21T15:53:59Z) - Assessing Dataset Bias in Computer Vision [0.0]
biases have the tendency to propagate to the models that train on them, often leading to a poor performance in the minority class.
We will apply several augmentation techniques on a sample of the UTKFace dataset, such as undersampling, geometric transformations, variational autoencoders (VAEs), and generative adversarial networks (GANs)
We were able to show that our model has a better overall performance and consistency on age and ethnicity classification on multiple datasets when compared with the FairFace model.
arXiv Detail & Related papers (2022-05-03T22:45:49Z) - Continual Learning for Blind Image Quality Assessment [80.55119990128419]
Blind image quality assessment (BIQA) models fail to continually adapt to subpopulation shift.
Recent work suggests training BIQA methods on the combination of all available human-rated IQA datasets.
We formulate continual learning for BIQA, where a model learns continually from a stream of IQA datasets.
arXiv Detail & Related papers (2021-02-19T03:07:01Z) - Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and
Wild [98.48284827503409]
We develop a textitunified BIQA model and an approach of training it for both synthetic and realistic distortions.
We employ the fidelity loss to optimize a deep neural network for BIQA over a large number of such image pairs.
Experiments on six IQA databases show the promise of the learned method in blindly assessing image quality in the laboratory and wild.
arXiv Detail & Related papers (2020-05-28T13:35:23Z)
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.