paper-with-me

Papers

Scale Contrastive Learning with Selective Attentions for Blind Image Quality Assessment

2024-11-13 · Zihao Huang, Xudong Li, Bohan Fu, Xiaohui Chu, Ke Li, Yunhang Shen, Yan Zhang

Blind image quality assessment (BIQA) serves as a fundamental task in computer vision, yet it often fails to consistently align with human subjective perception. Recent advances show that multi-scale evaluation strategies are promising due to their ability to replicate the hierarchical structure of human vision. However, the effectiveness of these strategies is limited by a lack of understanding of how different image scales influence perceived quality. This paper addresses two primary challenges: the significant redundancy of information across different scales, and the confusion caused by combining features from these scales, which may vary widely in quality. To this end, a new multi-scale BIQA framework is proposed, namely Contrast-Constrained Scale-Focused IQA Framework (CSFIQA). CSFIQA features a selective focus attention mechanism to minimize information redundancy and highlight critical quality-related information. Additionally, CSFIQA includes a scale-level contrastive learning module equipped with a noise sample matching mechanism to identify quality discrepancies across the same image content at different scales. By exploring the intrinsic relationship between image scales and the perceived quality, the proposed CSFIQA achieves leading performance on eight benchmark datasets, e.g., achieving SRCC values of 0.967 (versus 0.947 in CSIQ) and 0.905 (versus 0.876 in LIVEC).

📄 PDF Abstract BibTeX arXiv:2411.09007

Code (0)

등록된 구현이 없습니다.

Tasks

Blind Image Quality AssessmentContrastive LearningImage Quality Assessment

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Contrastive Learning 설명 없음
Focus 설명 없음
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising

2024-04-11 · Junyi Li, Zhilu Zhang, WangMeng Zuo

Blind-spot networks (BSN) have been prevalent neural architectures in self-supervised image denoising (SSID). However, most existing BSNs are conducted with convolution layers. Although transformers have shown the potent…

Computational EfficiencyDenoisingImage DenoisingImage Restoration+1

Feature Selective Transformer for Semantic Image Segmentation

2022-03-26 · Fangjian Lin, Tianyi Wu, Sitong Wu, Shengwei Tian 외

Recently, it has attracted more and more attentions to fuse multi-scale features for semantic image segmentation. Various works were proposed to employ progressive local or global fusion, but the feature fusions are not …

feature selectionImage SegmentationSegmentationSemantic Segmentation

Hierarchical Contrastive Learning for Pattern-Generalizable Image Corruption Detection

2023-08-27 · ICCV 2023 1 · Xin Feng, Yifeng Xu, Guangming Lu, Wenjie Pei

Effective image restoration with large-size corruptions, such as blind image inpainting, entails precise detection of corruption region masks which remains extremely challenging due to diverse shapes and patterns of corr…

Contrastive LearningImage InpaintingImage Restoration

Blind Image Super-Resolution via Contrastive Representation Learning

2021-07-01 · Jiahui Zhang, Shijian Lu, Fangneng Zhan, Yingchen Yu

Image super-resolution (SR) research has witnessed impressive progress thanks to the advance of convolutional neural networks (CNNs) in recent years. However, most existing SR methods are non-blind and assume that degrad…

Contrastive LearningImage Super-ResolutionRepresentation LearningSuper-Resolution

Statistical Test for Attention Map in Vision Transformer

2024-01-16 · Tomohiro Shiraishi, Daiki Miwa, Teruyuki Katsuoka, Vo Nguyen Le Duy 외

The Vision Transformer (ViT) demonstrates exceptional performance in various computer vision tasks. Attention is crucial for ViT to capture complex wide-ranging relationships among image patches, allowing the model to we…

Decision Making