Low-Quality Image Detection by Hierarchical VAE
Not on the map. Why?
Abstract (arXiv)
To make an employee roster, photo album, or training dataset of generative models, one needs to collect high-quality images while dismissing low-quality ones. This study addresses a new task of unsupervised detection of low-quality images. We propose a method that not only detects low-quality images with various types of degradation but also provides visual clues of them based on an observation that partial reconstruction by hierarchical variational autoencoders fails for low-quality images. The experiments show that our method outperforms several unsupervised out-of-distribution detection methods and also gives visual clues for low-quality images that help humans recognize them even in thumbnail view.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 35 references that are in the map. First posted on arXiv 20 Aug 2024.
Builds on
28 of 35 references.
References · 28
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
- 2018Deep Anomaly Detection with Outlier Exposurecited by 939
- 2016Pixel Recurrent Neural Networkscited by 814
- 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
- 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
- 2021Multi-attentional Deepfake Detectioncited by 339
- 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
- 2016Ladder Variational Autoencoderscited by 315
- 2020Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Imagescited by 261
16 more
- 2018Generalisation in humans and deep neural networkscited by 237
- 2020Classification-Based Anomaly Detection for General Datacited by 210
- 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
- 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
- 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
- 2022Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generationcited by 119
- 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 98
- 2017SafetyNet: Detecting and Rejecting Adversarial Examples Robustlycited by 76
- 2019The Odds are Odd: A Statistical Test for Detecting Adversarial Examplescited by 75
- 2021Hierarchical VAEs Know What They Don't Knowcited by 58
- 2019ML-LOO: Detecting Adversarial Examples with Feature Attributioncited by 48
- 2021Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Themcited by 46
- 2022Delving into Sequential Patches for Deepfake Detectioncited by 41
- 2020Head2Head: Video-based Neural Head Synthesiscited by 40
- 2021Towards Solving the DeepFake Problem : An Analysis on Improving DeepFake Detection using Dynamic Face Augmentationcited by 25
- 2021Robust outlier detection by de-biasing VAE likelihoodscited by 8
Built on by
Citing papers per year: 2025: 1.
1 paper.