Search Results for author:
Found 8 papers, 0 papers with code
NN-VVC: Versatile Video Coding boosted by self-supervisedly learned image coding for machines
To the best of our knowledge, this is the first research paper showing a hybrid video codec that outperforms VVC on multiple datasets and multiple machine vision tasks.
Bridging the gap between image coding for machines and humans
Image coding for machines (ICM) aims at reducing the bitrate required to represent an image while minimizing the drop in machine vision analysis accuracy.
Image coding for machines: an end-to-end learned approach
Over recent years, deep learning-based computer vision systems have been applied to images at an ever-increasing pace, oftentimes representing the only type of consumption for those images.
Learned Image Coding for Machines: A Content-Adaptive Approach
One possible solution approach consists of adapting current human-targeted image and video coding standards to the use case of machine consumption.
Evolving Self-supervised Neural Networks: Autonomous Intelligence from Evolved Self-teaching
This paper presents a technique called evolving self-supervised neural networks - neural networks that can teach themselves, intrinsically motivated, without external supervision or reward.
Evolving Self-taught Neural Networks: The Baldwin Effect and the Emergence of Intelligence
Moreover, the self-taught neural network is the product of the interplay between evolution and learning.
Theoretical Guarantees of Deep Embedding Losses Under Label Noise
Collecting labeled data to train deep neural networks is costly and even impractical for many tasks.
Improving speaker turn embedding by crossmodal transfer learning from face embedding
Learning speaker turn embeddings has shown considerable improvement in situations where conventional speaker modeling approaches fail.
