L e a p M i n d
T e c h B l o g

Recent Posts

外観検査向け異常検知手法に関する論文紹介: PatchCore

published on

LeapMindの花元です。

異常検知、してますか？

学習済み深層学習モデルと近傍法を使って外観検査向け異常検知をしたくなること、長い人生で、たまにはありますよね。今日は外観検査向け異常検知の手法であり、CVPR 2022に採択されているPatchCoreのアルゴリズムを紹介したいと思います。PatchCoreの概要については前回の記事を参照してください。

Read More...

Pixel Embedding for Quantized Neural Networks

published on
Hi, I’m Joel from LeapMind. For this blog, I’ll write a little about pixel embedding, which enables fast inference of the first layer of a quantized neural network. This has been very useful for me recently. If you work with quantized neural networks, maybe it can be useful for you too. Background Neural networks can perform various computer vision tasks, which receive images as input. For example, the noise reduction task. Read More...

Tags

algorithm (1) anomaly-detection (4) buildkite (2) ci (2) dataset (1) deep-learning (9) gcp (1) graph-theory (1) hackdays (1) hydra (1) image-restoration (1) infrastructure (2) kubernetes (1) lightning (1) noise-reduction (1) object-detection (1) patchcore (1) project-organization (1) pytorch (1) quantized (1) skip-connection (1) voice-cloning (1)