A New Benchmark and Progress Toward Improved Weakly Supervised Learning

06/30/2018
by   Jason Ramapuram, et al.
0

Knowledge Matters: Importance of Prior Information for Optimization [7], by Gulcehre et. al., sought to establish the limits of current black-box, deep learning techniques by posing problems which are difficult to learn without engineering knowledge into the model or training procedure. In our work, we completely solve the previous Knowledge Matters problem using a generic model, pose a more difficult and scalable problem, All-Pairs, and advance this new problem by introducing a new learned, spatially-varying histogram model called TypeNet which outperforms conventional models on the problem. We present results on All-Pairs where our model achieves 100 ResNet models achieve 79 order of magnitude smaller than Resnet-34. The challenge of solving larger-scale All-Pairs problems with high accuracy is presented to the community for investigation.

READ FULL TEXT

page 3

page 4

page 13

research
10/24/2020

Stable ResNet

Deep ResNet architectures have achieved state of the art performance on ...
research
04/14/2021

A Weakly Supervised Model for Solving Math word Problems

Solving math word problems (MWPs) is an important and challenging proble...
research
06/02/2021

Weakly Supervised Learning Creates a Fusion of Modeling Cultures

The past two decades have witnessed the great success of the algorithmic...
research
03/16/2018

Adversarial Logit Pairing

In this paper, we develop improved techniques for defending against adve...
research
06/21/2015

Extreme Extraction: Only One Hour per Relation

Information Extraction (IE) aims to automatically generate a large knowl...
research
06/20/2023

A Model-free Closeness-of-influence Test for Features in Supervised Learning

Understanding the effect of a feature vector x ∈ℝ^d on the response valu...
research
08/18/2019

Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning

We propose to learn a 3D pose estimator by distilling knowledge from Non...

Please sign up or login with your details

Forgot password? Click here to reset