A comeback of signal processing? A video from authors and from Yannic, and the arxiv paper. btw, another video presentation of implicit representation.

Some remarks:

  1. Represent signals as functions instead multidimensional data (not a completely new idea as the authors pointed out)
  2. Match not just the signal itself but also its derivative
  3. Use sinsoidal activation function. This allows derivative of the network is still well-defined (and still a siren).



A very nice presentation (as always) of CornerNet by Yannic Kilcher. The key ideas are push-pull losses of corner embeddings and corner pooling. The ideas are simple and intuitive but very well excecuted. The authors have include ablation study for the gain of corner pooling. Their result is competitive with other 1 stage approach, better than YoloV3 but worse than YoloV4. And they also tested that when ground truth corner detections were used, their AP almost doubles. This illustrated that corner detection is their main bottleneck.

Copyright OU-Tulsa Lab of Image and Information Processing 2020
Tech Nerd theme designed by Siteturner