Search Results for author:
Found 11 papers, 4 papers with code
Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent
The search for a general model that can operate seamlessly across multiple domains remains a key goal in machine learning research.
Look Beyond Bias with Entropic Adversarial Data Augmentation
Deep neural networks do not discriminate between spurious and causal patterns, and will only learn the most predictive ones while ignoring the others.
Learning Less Generalizable Patterns with an Asymmetrically Trained Double Classifier for Better Test-Time Adaptation
Indeed, test-time adaptation methods usually have to rely on a limited representation because of the shortcut learning phenomenon: only a subset of the available predictive patterns is learned with standard training.
Cell-Free Latent Go-Explore
In this paper, we introduce Latent Go-Explore (LGE), a simple and general approach based on the Go-Explore paradigm for exploration in reinforcement learning (RL).
Multi-Goal Reinforcement Learning environments for simulated Franka Emika Panda robot
This technical report presents panda-gym, a set Reinforcement Learning (RL) environments for the Franka Emika Panda robot integrated with OpenAI Gym.
Encouraging Intra-Class Diversity Through a Reverse Contrastive Loss for Better Single-Source Domain Generalization
Traditional deep learning algorithms often fail to generalize when they are tested outside of the domain of the training data.
Scoring Graspability based on Grasp Regression for Better Grasp Prediction
Therefore, in this paper, we extend a state-of-the-art neural network with a scorer that evaluates the graspability of a given position, and introduce a novel loss function which correlates regression of grasp parameters with graspability score.
Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image
We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets.
Developmental Bayesian Optimization of Black-Box with Visual Similarity-Based Transfer Learning
In simulation, we demonstrate the benefit of the transfer learning based on visual similarity, as opposed to an amnesic learning (i. e. learning from scratch all the time).
Jacquard: A Large Scale Dataset for Robotic Grasp Detection
Jacquard is built on a subset of ShapeNet, a large CAD models dataset, and contains both RGB-D images and annotations of successful grasping positions based on grasp attempts performed in a simulated environment.
Object segmentation in depth maps with one user click and a synthetically trained fully convolutional network
We thus propose a step towards a practical interactive application for generating an object-oriented robotic grasp, requiring as inputs only one depth map of the scene and one user click on the next object to extract.
