This document summarizes recent advances in single image super-resolution (SISR) using deep learning methods. It discusses early SISR networks like SRCNN, VDSR and ESPCN. SRResNet is presented as a baseline method, incorporating residual blocks and pixel shuffle upsampling. SRGAN and EDSR are also introduced, with EDSR achieving state-of-the-art PSNR results. The relationship between reconstruction loss, perceptual quality and distortion is examined. While PSNR improves yearly, a perception-distortion tradeoff remains. Developments are ongoing to produce outputs that are both accurately restored and naturally perceived.
Several recent papers have explored self-supervised learning methods for vision transformers (ViT). Key approaches include:
1. Masked prediction tasks that predict masked patches of the input image.
2. Contrastive learning using techniques like MoCo to learn representations by contrasting augmented views of the same image.
3. Self-distillation methods like DINO that distill a teacher ViT into a student ViT using different views of the same image.
4. Hybrid approaches that combine masked prediction with self-distillation, such as iBOT.
This document provides an overview of POMDP (Partially Observable Markov Decision Process) and its applications. It first defines the key concepts of POMDP such as states, actions, observations, and belief states. It then uses the classic Tiger problem as an example to illustrate these concepts. The document discusses different approaches to solve POMDP problems, including model-based methods that learn the environment model from data and model-free reinforcement learning methods. Finally, it provides examples of applying POMDP to games like ViZDoom and robot navigation problems.
文献紹介:TSM: Temporal Shift Module for Efficient Video UnderstandingToru Tamaki
Ji Lin, Chuang Gan, Song Han; TSM: Temporal Shift Module for Efficient Video Understanding, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 7083-7093
https://openaccess.thecvf.com/content_ICCV_2019/html/Lin_TSM_Temporal_Shift_Module_for_Efficient_Video_Understanding_ICCV_2019_paper.html
Several recent papers have explored self-supervised learning methods for vision transformers (ViT). Key approaches include:
1. Masked prediction tasks that predict masked patches of the input image.
2. Contrastive learning using techniques like MoCo to learn representations by contrasting augmented views of the same image.
3. Self-distillation methods like DINO that distill a teacher ViT into a student ViT using different views of the same image.
4. Hybrid approaches that combine masked prediction with self-distillation, such as iBOT.
This document provides an overview of POMDP (Partially Observable Markov Decision Process) and its applications. It first defines the key concepts of POMDP such as states, actions, observations, and belief states. It then uses the classic Tiger problem as an example to illustrate these concepts. The document discusses different approaches to solve POMDP problems, including model-based methods that learn the environment model from data and model-free reinforcement learning methods. Finally, it provides examples of applying POMDP to games like ViZDoom and robot navigation problems.
文献紹介:TSM: Temporal Shift Module for Efficient Video UnderstandingToru Tamaki
Ji Lin, Chuang Gan, Song Han; TSM: Temporal Shift Module for Efficient Video Understanding, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 7083-7093
https://openaccess.thecvf.com/content_ICCV_2019/html/Lin_TSM_Temporal_Shift_Module_for_Efficient_Video_Understanding_ICCV_2019_paper.html
Math in Machine Learning / PCA and SVD with ApplicationsKenji Hiranabe
Math in Machine Learning / PCA and SVD with Applications
機会学習の数学とPCA/SVD
Colab での練習コードつきです.コードはこちら.
https://colab.research.google.com/drive/1YZgZWX5a7_MGA__HV2bybSuJsqkd4XxD?usp=sharing
Towards Total Recall in Industrial Anomaly Detectionharmonylab
公開URL:https://openaccess.thecvf.com/content/CVPR2022/papers/Roth_Towards_Total_Recall_in_Industrial_Anomaly_Detection_CVPR_2022_paper.pdf
出典:Karsten Roth, Latha Pemula, Joaquin Zepeda, Bernhard Schölkopf, Thomas Brox, Peter Gehler: Towards Total Recall in Industrial Anomaly Detection, Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14318-14328 (2022)
概要:本論文では位置情報を考慮した特徴量の集合和であるメモリバンクとCoresetによる画像パッチ特徴量の削減を行うPatchCoreアルゴリズムを提案する.結果として、異常検出のベンチマークであるMVTecにおいてAUROC99%以上の精度を出力し,2022年時点でのSoTAを記録した.また,PatchCoreによる特徴量削減により,学習のサンプル数を20%に減らした場合でも以前のSoTAに匹敵する精度となった.
Explanation in Machine Learning and Its ReliabilitySatoshi Hara
This document summarizes a presentation on explanation in machine learning. It discusses two types of explanations: saliency maps and similar examples. Saliency maps highlight important regions of an input that influenced a prediction. Similar examples provide instances from a database that are similar to the input. The document notes that the reliability of explanations has become a key concern, as explanations may not be valid or could be used maliciously. It reviews research evaluating the faithfulness and plausibility of explanations, and proposes tests like parameter randomization to evaluate faithfulness. The talk concludes that generating fake explanations could allow unfair models to appear fair, highlighting a risk of "fairwashing" that more research is needed to address.
Convex Hull Approximation of Nearly Optimal Lasso SolutionsSatoshi Hara
Satoshi Hara, Takanori Maehara. Convex Hull Approximation of Nearly Optimal Lasso Solutions. In Proceedings of 16th Pacific Rim International Conference on Artificial Intelligence, Part II, pages 350--363, 2019.
Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and...Satoshi Hara
【NeurIPS 2018 読み会 in 京都】
Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds
https://papers.nips.cc/paper/8120-theoretical-linear-convergence-of-unfolded-ista-and-its-practical-weights-and-thresholds
* Satoshi Hara and Kohei Hayashi. Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach. AISTATS'18 (to appear).
arXiv ver.: https://arxiv.org/abs/1606.09066#
* GitHub
https://github.com/sato9hara/defragTrees
ERATO感謝祭 Season IV
【参考】Satoshi Hara and Takanori Maehara. Enumerate Lasso Solutions for Feature Selection. In Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI'17), pages 1985--1991, 2017.
KDD'17読み会:Anomaly Detection with Robust Deep Autoencoders
1. Anomaly Detection with Robust Deep
Autoencoders
Chong Zhou, Randy C. Paffenroth
Worcester Polytechnic Institute
1
原 聡
大阪大学 産業科学研究所
KDD2017勉強会@京大, 2017/10/7
12. Robust PCAと外れ値検知
n Robust PCAでは低ランク行列𝑈とノイズ行列𝑅を同時推定する。
n ノイズの値が大きいデータ点𝑥(𝑛)が外れ値と言える。
n 例:動画の各フレームを背景(低ランク要素)と
外れ値の要因(動体)へと分解。
n [引用元] Emmanuel J. Candes, Xiaodong Li, Yi Ma,
John Wright. "Robust Principal Component Analysis?”,
2009.
12
28. まとめ
n 従来のAutoencoderでは、データセット内の外れ値は検知できなかった。
n 外れ値検知のためのRobust Autoencoderを提案。
• PCAをRobust PCAに拡張する流れをAutoencoderに適用。
• 交互最適化による学習方法を提案。
n MNIST実験でRobust Autoencoderの有効性を検証。
n コード: https://github.com/zc8340311/RobustAutoencoder
28