paper-with-me

Papers

Reducing the Amount of Real World Data for Object Detector Training with Synthetic Data

2022-01-31 · Sven Burdorf, Karoline Plum, Daniel Hasenklever

A number of studies have investigated the training of neural networks with synthetic data for applications in the real world. The aim of this study is to quantify how much real world data can be saved when using a mixed dataset of synthetic and real world data. By modeling the relationship between the number of training examples and detection performance by a simple power law, we find that the need for real world data can be reduced by up to 70% without sacrificing detection performance. The training of object detection networks is especially enhanced by enriching the mixed dataset with classes underrepresented in the real world dataset. The results indicate that mixed datasets with real world data ratios between 5% and 20% reduce the need for real world data the most without reducing the detection performance.

📄 PDF Abstract BibTeX arXiv:2202.00632

Code (0)

등록된 구현이 없습니다.

Tasks

object-detectionObject Detection

Similar Papers 제목 키워드 기반

WorldGen: A Large Scale Generative Simulator

2022-10-03 · Chahat Deep Singh, Riya Kumari, Cornelia Fermüller, Nitin J. Sanket 외

In the era of deep learning, data is the critical determining factor in the performance of neural network models. Generating large datasets suffers from various difficulties such as scalability, cost efficiency and photo…

ObjectOptical Flow Estimation

SIM2REALVIZ: Visualizing the Sim2Real Gap in Robot Ego-Pose Estimation

2021-09-24 · Theo Jaunet, Guillaume Bono, Romain Vuillemot, Christian Wolf

The Robotics community has started to heavily rely on increasingly realistic 3D simulators for large-scale training of robots on massive amounts of data. But once robots are deployed in the real world, the simulation gap…

Pose Estimation

DayDreamer: World Models for Physical Robot Learning

2022-06-28 · Philipp Wu, Alejandro Escontrela, Danijar Hafner, Ken Goldberg 외

To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its deplo…

Deep Reinforcement LearningNavigatereinforcement-learningReinforcement Learning (RL)

Learning Gentle Grasping Using Vision, Sound, and Touch

2025-03-11 · Ken Nakahara, Roberto Calandra

In our daily life, we often encounter objects that are fragile and can be damaged by excessive grasping force, such as fruits. For these objects, it is paramount to grasp gently -- not using the maximum amount of force p…

Acquire, Augment, Segment & Enjoy: Weakly Supervised Instance Segmentation of Supermarket Products

2018-07-05 · Patrick Follmann, Bertram Drost, Tobias Böttger

Grocery stores have thousands of products that are usually identified using barcodes with a human in the loop. For automated checkout systems, it is necessary to count and classify the groceries efficiently and robustly.…

Instance SegmentationObjectSemantic SegmentationWeakly-supervised instance segmentation