114 citations · 144 across the 12 of their papers we have counts for
14 papers
Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How
Sebastian Pineda Arango, Fabio Ferreira, Arlind Kadra +2
With the ever-increasing number of pretrained models, machine learning practitioners are continuously faced with which pretrained model to use, and how to finetune it for a new dat…
On the Importance of Hyperparameters and Data Augmentation for Self-Supervised Learning
Diane Wagner, Fabio Ferreira, Danny Stoll +3
Self-Supervised Learning (SSL) has become a very active area of Deep Learning research where it is heavily used as a pre-training method for classification and other tasks. However…
Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification
Adrian El Baz, Ihsan Ullah, Edesio Alcobaça +17
Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resourc…
Zero-Shot AutoML with Pretrained Models
Ekrem Öztürk, Fabio Ferreira, Hadi S. Jomaa +3
Given a new dataset D and a low compute budget, how should we choose a pre-trained model to fine-tune to D, and set the fine-tuning hyperparameters without risking overfitting, par…
Learning Synthetic Environments and Reward Networks for Reinforcement Learning
Fabio Ferreira, Thomas Nierhoff, Andreas Saelinger +1
We introduce Synthetic Environments (SEs) and Reward Networks (RNs), represented by neural networks, as proxy environment models for training Reinforcement Learning (RL) agents. We…
Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019
Zhengying Liu, Adrien Pavao, Zhen Xu +22
This paper reports the results and post-challenge analyses of ChaLearn's AutoDL challenge series, which helped sorting out a profusion of AutoML solutions for Deep Learning (DL) th…
Learning Synthetic Environments for Reinforcement Learning with Evolution Strategies
Fabio Ferreira, Thomas Nierhoff, Frank Hutter
This work explores learning agent-agnostic synthetic environments (SEs) for Reinforcement Learning. SEs act as a proxy for target environments and allow agents to be trained more e…
Learning Visual Dynamics Models of Rigid Objects using Relational Inductive Biases
Fabio Ferreira, Lin Shao, Tamim Asfour +1
Endowing robots with human-like physical reasoning abilities remains challenging. We argue that existing methods often disregard spatio-temporal relations and by using Graph Neural…
UniGrasp: Learning a Unified Model to Grasp with Multifingered Robotic Hands
Lin Shao, Fabio Ferreira, Mikael Jorda +6
To achieve a successful grasp, gripper attributes such as its geometry and kinematics play a role as important as the object geometry. The majority of previous work has focused on…
MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning
Raghu Rajan, Jessica Lizeth Borja Diaz, Suresh Guttikonda +4
We present MDP Playground, a testbed for Reinforcement Learning (RL) agents with dimensions of hardness that can be controlled independently to challenge agents in different ways a…
Noise Regularization for Conditional Density Estimation
Jonas Rothfuss, Fabio Ferreira, Simon Boehm +4
Modelling statistical relationships beyond the conditional mean is crucial in many settings. Conditional density estimation (CDE) aims to learn the full conditional probability den…
Conditional Density Estimation with Neural Networks: Best Practices and Benchmarks
Jonas Rothfuss, Fabio Ferreira, Simon Walther +1
Given a set of empirical observations, conditional density estimation aims to capture the statistical relationship between a conditional variable and a dependent varia…
Introducing the Simulated Flying Shapes and Simulated Planar Manipulator Datasets
Fabio Ferreira, Jonas Rothfuss, Eren Erdal Aksoy +2
We release two artificial datasets, Simulated Flying Shapes and Simulated Planar Manipulator that allow to test the learning ability of video processing systems. In particular, the…
Deep Episodic Memory: Encoding, Recalling, and Predicting Episodic Experiences for Robot Action Execution
Jonas Rothfuss, Fabio Ferreira, Eren Erdal Aksoy +2
We present a novel deep neural network architecture for representing robot experiences in an episodic-like memory which facilitates encoding, recalling, and predicting action exper…