태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Edge Detection is a fundamental image processing technique which involves computing an image gradient to quantify the magnitude and direction of edges in an image. Image gradients are used in various downstream tasks in computer vision such as line detection, feature detection, and image classification.
Source: Artistic Enhancement and Style Transfer of Image Edges using Directional Pseudo-coloring
( Image credit: Kornia )
관련 논문에서 소개한 기법입니다. 이 태스크에서의 평가 여부는 평가 결과에서 확인하세요.
A Harmonic Network, or Harm-Net, is a type of convolutional neural network that replaces convolutional layers with "harmonic blocks" that use Discrete Cosine Transform (DCT) filters. These blocks can be useful in truncating high-frequency information (possible due to the redundancies in the spectral domain).
Harmonic Convolutional Networks based on Discrete Cosine Transform
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.