mlsanityData to 7 Oct 2026

Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective

arXiv 2303.14968 ↗First posted 27 Mar 2023cs.CV cs.LGcited by 276

Not on the map. Why?

Cited by 38 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We aim at advancing blind image quality assessment (BIQA), which predicts the human perception of image quality without any reference information. We develop a general and automated multitask learning scheme for BIQA to exploit auxiliary knowledge from other tasks, in a way that the model parameter sharing and the loss weighting are determined automatically. Specifically, we first describe all candidate label combinations (from multiple tasks) using a textual template, and compute the joint probability from the cosine similarities of the visual-textual embeddings. Predictions of each task can be inferred from the joint distribution, and optimized by carefully designed loss functions. Through comprehensive experiments on learning three tasks - BIQA, scene classification, and distortion type identification, we verify that the proposed BIQA method 1) benefits from the scene classification and distortion type identification tasks and outperforms the state-of-the-art on multiple IQA datasets, 2) is more robust in the group maximum differentiation competition, and 3) realigns the quality annotations from different IQA datasets more effectively. The source code is available at https://github.com/zwx8981/LIQE.

Key facts. Cited by 276 papers in the map (data through 7 Oct 2026). Builds on 45 of its 83 references that are in the map. First posted on arXiv 27 Mar 2023.

Builds on

45 of 83 references.

References · 45

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  6. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  7. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  8. 2021Grounded Language-Image Pre-trainingcited by 1,147
  9. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  10. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  11. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  12. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 816
33 more
  1. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
  2. 2022Language-driven Semantic Segmentationcited by 711
  3. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  4. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 529
  5. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  6. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  7. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 351
  8. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 301
  9. 2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 224
  10. 2019Pareto Multi-Task Learningcited by 224
  11. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 221
  12. 2015Massive Online Crowdsourced Study of Subjective and Objective Picture Qualitycited by 208
  13. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  14. 2020Fast Differentiable Sorting and Rankingcited by 196
  15. 2020PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restorationcited by 177
  16. 2021No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistencycited by 165
  17. 2019AdaShare: Learning What To Share For Efficient Deep Multi-Task Learningcited by 159
  18. 2017RankIQA: Learning from Rankings for No-reference Image Quality Assessmentcited by 150
  19. 2020MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessmentcited by 144
  20. 2020Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wildcited by 134
  21. 2021Image Quality Assessment using Contrastive Learningcited by 95
  22. 2019Branched Multi-Task Networks: Deciding What Layers To Sharecited by 76
  23. 2022Auto-Lambda: Disentangling Dynamic Task Relationshipscited by 73
  24. 2016Perceptual Quality Prediction on Authentically Distorted Images Using a Bag of Features Approachcited by 71
  25. 2022CLIPasso: Semantically-Aware Object Sketchingcited by 57
  26. 2020Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessmentcited by 54
  27. 2022Task Adaptive Parameter Sharing for Multi-Task Learningcited by 42
  28. 2021Continual Learning for Blind Image Quality Assessmentcited by 36
  29. 2022Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loopcited by 30
  30. 2020Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessmentcited by 24
  31. 2021LIQA: Lifelong Blind Image Quality Assessmentcited by 20
  32. 2021Task-Specific Normalization for Continual Learning of Blind Image Quality Modelscited by 18
  33. 2021Troubleshooting Blind Image Quality Models in the Wildcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 20; 2024: 87; 2025: 92; 2026: 77.

276 papers.

Sort:

By area:

  1. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 489
  2. 2023TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessmentcited by 220
  3. 2024Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animationcited by 172
  4. 2023Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Modelscited by 152
  5. 2023AGIQA-3K: An Open Database for AI-Generated Image Quality Assessmentcited by 142
  6. 2025Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distributioncited by 139
  7. 2023Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Modelscited by 104
  8. 2024Towards Open-ended Visual Quality Comparisoncited by 85
  9. 2025VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rankcited by 77
  10. 2024Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Comparecited by 66
  11. 2025DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolutioncited by 50
  12. 2023Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approachcited by 45
38 more
  1. 2024A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessmentcited by 43
  2. 2024Image Watermarks are Removable Using Controllable Regeneration from Clean Noisecited by 43
  3. 2023MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learningcited by 42
  4. 2025Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animationcited by 41
  5. 2023Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Modelscited by 38
  6. 2024KVQ: Kwai Video Quality Assessment for Short-form Videoscited by 38
  7. 2024Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Datasetcited by 38
  8. 2024Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Drivingcited by 35
  9. 2025Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumptioncited by 34
  10. 2024AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessmentcited by 33
  11. 2025JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restorationcited by 32
  12. 2024Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessmentcited by 31
  13. 2024CosmicMan: A Text-to-Image Foundation Model for Humanscited by 30
  14. 2024NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Resultscited by 29
  15. 2024R-Bench: Are your Large Multimodal Model Robust to Real-world Corruptions?cited by 29
  16. 2023On Diversified Preferences of Large Language Model Alignmentcited by 26
  17. 2024Quality Assessment in the Era of Large Models: A Surveycited by 26
  18. 2025WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild?cited by 26
  19. 2024AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMMcited by 24
  20. 2025LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMscited by 24
  21. 2025X2Edit: Revisiting Arbitrary-Instruction Image Editing through Self-Constructed Data and Task-Aware Representation Learningcited by 24
  22. 2025Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazingcited by 23
  23. 2023Exploring the Naturalness of AI-Generated Imagescited by 22
  24. 20242AFC Prompting of Large Multimodal Models for Image Quality Assessmentcited by 20
  25. 2024NTIRE 2024 Quality Assessment of AI-Generated Content Challengecited by 20
  26. 2024Enhancing Blind Video Quality Assessment with Rich Quality-aware Featurescited by 19
  27. 2025SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Modelscited by 19
  28. 2023Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessmentcited by 17
  29. 2024DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformercited by 17
  30. 2024Beyond Pixels: Text Enhances Generalization in Real-World Image Restorationcited by 17
  31. 2023Towards Robust Text-Prompted Semantic Criterion for In-the-Wild Video Quality Assessmentcited by 16
  32. 2024UHD-IQA Benchmark Database: Pushing the Boundaries of Blind Photo Quality Assessmentcited by 16
  33. 2024VQA2: Visual Question Answering for Video Quality Assessmentcited by 15
  34. 2024Video Quality Assessment: A Comprehensive Surveycited by 15
  35. 2024DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wildcited by 14
  36. 2024CLIP-AGIQA: Boosting the Performance of AI-Generated Image Quality Assessment with CLIPcited by 14
  37. 2025MVPortrait: Text-Guided Motion and Emotion Control for Multi-view Vivid Portrait Animationcited by 14
  38. 2025NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Resultscited by 14

50 most cited of 276 All 276 (JSON)