Lossy common information in a learnable Gray-Wyner Network
Isolate the common information between two dependent computer vision tasks.
Multitask Learning
Towards task-compatible compressible representations
Task reconstruction loss acts as a regularizer, increasing rate-distortion performance in coding for humans and machines.
Conditional and residual methods in scalable coding for humans and machines
A comparison between conditional and residual entropy codecs for a two-channel systems of tasks with nested information.