Sökning: "Domänadaption"

Hittade 4 uppsatser innehållade ordet Domänadaption.

1. 1. Domain Adaptation Of Front View Synthetic Point Clouds Using GANs For Autonomous Driving

   Master-uppsats, KTH/Väg- och spårfordon samt konceptuell fordonsdesign

   Författare :Friedemann Kleinsteuber; [2023]
   Nyckelord :LiDAR; Domain Adaptation; GAN; CycleGAN; Simulation; LiDAR; Domänadaption; GAN; CycleGAN; Simulation;

   Sammanfattning : The perception of the environment is one of the main enablers of Autonomous Driving and is driven by Cameras, RADAR, and LiDAR sensors. Deep Learning algorithms used in perception need a vast amount of labeled, high-quality data which is costly to obtain for LiDAR sensors. LÄS MER

3. 2. Data Synthesis in Deep Learning for Object Detection

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Josef Haddad; [2021]
   Nyckelord :Deep Learning; Computer vision; Object detection; Synthetic data; Domain Adaptation; Machine Learning; Djupinlärning; Datorseende; Objektdetektion; Syntetiskt data; Domänadaption; Maskininlärning;

   Sammanfattning : Deep neural networks typically require large amounts of labeled data for training, but a problem is that collecting data can be expensive. Our study aims at revealing insights into how training with synthetic data affects performance in real-world object detection tasks. LÄS MER

4. 3. Musical Instrument Activity Detection using Self-Supervised Learning and Domain Adaptation

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Carl Nyströmer; [2020]
   Nyckelord :Audio classification; music information retrieval; musical instrument recognition; musical instrument activity detection; self-supervised learning; domain adaptation; Ljudklassificering; hämtning av musikinformation; musikintrumentsigenkänning; instrumentaktivitetsigenkänning; självövervakad inlärning; domänadaption;

   Sammanfattning : With the ever growing media and music catalogs, tools that search and navigate this data are important. For more complex search queries, meta-data is needed, but to manually label the vast amounts of new content is impossible. LÄS MER

5. 4. Domain Adaptation of IMU sensors using Generative Adversarial Networks

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Saieshwar Radhakrishnan; [2020]
   Nyckelord :Autonomous vehicles; sensors; internal dynamics; Inertial Measurement Unit; covalidation; Generative Adversarial Network; WaveNets; LSTM.; Autonoma fordon; sensorer; intern dynamik; tröghetsmätningsenhet; samvalidering; Generative Adversarial Network; WaveNets; LSTM.;

   Sammanfattning : Autonomous vehicles rely on sensors for a clear understanding of the environment and in a heavy duty truck, the sensors are placed at multiple locations like the cabin, chassis and the trailer in order to increase the field of view and reduce the blind spot area. Usually, these sensors perform best when they are stationary relative to the ground, hence large and fast movements, which are quite common in a truck, may lead to performance reduction, erroneous data or in the worst case, a sensor failure. LÄS MER