Search Results for author:
Found 15 papers, 5 papers with code
Domain Adversarial Training: A Game Perspective
Defining optimal solutions in domain-adversarial training as a local Nash equilibrium, we show that gradient descent in domain-adversarial training can violate the asymptotic convergence guarantees of the optimizer, oftentimes hindering the transfer performance.
Federated Learning with Heterogeneous Architectures using Graph HyperNetworks
Standard Federated Learning (FL) techniques are limited to clients with identical network architectures.
Scalable Neural Data Server: A Data Recommender for Transfer Learning
Thus, the computational cost to each user grows with the number of sources and requires an expensive training step for each data provider. To address these issues, we propose Scalable Neural Data Server (SNDS), a large-scale search engine that can theoretically index thousands of datasets to serve relevant ML data to end users.
Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation
Alternative solutions seek to exploit driving simulators that can generate large amounts of labeled data with a plethora of content variations.
f-Domain-Adversarial Learning: Theory and Algorithms
Unsupervised domain adaptation is used in many machine learning applications where, during training, a model has access to unlabeled data in the target domain, and a related labeled dataset.
Complex Momentum for Optimization in Games
We generalize gradient descent with momentum for optimization in differentiable games to have complex-valued momentum.
f-Domain-Adversarial Learning: Theory and Algorithms for Unsupervised Domain Adaptation with Neural Networks
We provide empirical results for several f-divergences and show that some, not considered previously in domain-adversarial learning, achieve state-of-the-art results in practice.
Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data
NDS consists of a dataserver which indexes several large popular image datasets, and aims to recommend data to a client, an end-user with a target application with its own small labeled dataset.
Neural Turtle Graphics for Modeling City Road Layouts
We propose Neural Turtle Graphics (NTG), a novel generative model for spatial graphs, and demonstrate its applications in modeling city road layouts.
Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
Here, we propose a new two-stream CNN architecture for semantic segmentation that explicitly wires shape information as a separate processing branch, i. e. shape stream, that processes information in parallel to the classical stream.
Ranked #17 on
Semantic Segmentation
on Cityscapes test
Meta-Sim: Learning to Generate Synthetic Datasets
Training models to high-end performance requires availability of large labeled datasets, which are expensive to get.
Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations
We further reason about true object boundaries during training using a level set formulation, which allows the network to learn from misaligned labels in an end-to-end fashion.
Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data
Moreover, synthetic SDR data combined with real KITTI data outperforms real KITTI data alone.
Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization
We present a system for training deep neural networks for object detection using synthetic images.
Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++
Manually labeling datasets with object masks is extremely time consuming.
