Nicolas Carion and colleagues, 2020
We present a new method that views object detection as a direct set prediction problem.
Don't Just Read it – Explore It
We present a new method that views object detection as a direct set prediction problem.
Our novel Focal Loss focuses training on a sparse set of hard examples.
Our key insight is to build fully convolutional networks that take input of arbitrary size and produce correspondingly-sized output.
An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position.
The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization.
We propose a new global log-bilinear regression model that combines the advantages of the two major model families in the literature.
This paper presents a method for extracting distinctive invariant features from images.
Q-learning is a simple way for agents to learn how to act optimally in controlled Markovian domains.
We propose two novel model architectures for computing continuous vector representations of words from very large data sets.
REINFORCE algorithms are shown to make weight adjustments in a direction that lies along the gradient of expected reinforcement.
A fuzzy set is a class of objects with a continuum of grades of membership.