Posts
-
Most of the Recent Advancements in Transformers are Useless
Most of recent Transformer Modifications Fail To Transfer Across Implementations and Applications
-
New DALL-E? Paint by Word
Image editing by painting a mask and specifying any text description to guide the image generation. TL;DR: Just train a StyleGAN / BigGAN generator and then, to edit an image region, just optimize the masked latent code using pretrained CLIP as a loss.
-
How to easily edit and compose images using GANs like in Photoshop
Using StyleGAN latent space regression to analyze and create image collages with GANs.
-
You don't need EfficientNets. Simple tricks make ResNets better and faster than EfficientNets
Revisiting ResNets: Improved Training and Scaling Strategies. New family of architectures - ResNet-RS.
-
Winning solution for Kaggle challenge: Lyft Motion Prediction for Autonomous Vehicles
Competition 3rd Place Solution: Agents’ future motion prediction with CNN + Set Transformer.
-
Multi-Animal Linear model (SMAL): Modeling the 3D Shape and Pose of Animals
“3D Menagerie: Modeling the 3D Shape and Pose of Animal”, Zuffi et al, CVPR 2017.
-
A Container for Insert, Delete and GetRandom in O(1) Time
I have encountered a curious problem at leetcode. You need to come up with a data structure that supports insertion, removing and retrieving a uniformly random element in average O(1) time. This problem is interesting because it shows how one can design data structures with amortized constant time complexity.
-
Binary Tree Right Side View
Imagine yourself standing on the right side of it. Now return the values of the nodes you can see ordered from top to bottom.
Gradient Dude