4 code implementations • ICCV 2019 • Towaki Takikawa, David Acuna, Varun Jampani, Sanja Fidler
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 #24 on Semantic Segmentation on Cityscapes test
3 code implementations • CVPR 2018 • David Acuna, Huan Ling, Amlan Kar, Sanja Fidler
Manually labeling datasets with object masks is extremely time consuming.
1 code implementation • CVPR 2019 • David Acuna, Amlan Kar, Sanja Fidler
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.
1 code implementation • 18 Apr 2018 • Jonathan Tremblay, Aayush Prakash, David Acuna, Mark Brophy, Varun Jampani, Cem Anil, Thang To, Eric Cameracci, Shaad Boochoon, Stan Birchfield
We present a system for training deep neural networks for object detection using synthetic images.
1 code implementation • 21 Jun 2021 • David Acuna, Guojun Zhang, Marc T. Law, Sanja Fidler
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.
no code implementations • 23 Oct 2018 • Aayush Prakash, Shaad Boochoon, Mark Brophy, David Acuna, Eric Cameracci, Gavriel State, Omer Shapira, Stan Birchfield
Moreover, synthetic SDR data combined with real KITTI data outperforms real KITTI data alone.
no code implementations • ICCV 2019 • Amlan Kar, Aayush Prakash, Ming-Yu Liu, Eric Cameracci, Justin Yuan, Matt Rusiniak, David Acuna, Antonio Torralba, Sanja Fidler
Training models to high-end performance requires availability of large labeled datasets, which are expensive to get.
no code implementations • ICCV 2019 • Hang Chu, Daiqing Li, David Acuna, Amlan Kar, Maria Shugrina, Xinkai Wei, Ming-Yu Liu, Antonio Torralba, Sanja Fidler
We propose Neural Turtle Graphics (NTG), a novel generative model for spatial graphs, and demonstrate its applications in modeling city road layouts.
no code implementations • CVPR 2020 • Xi Yan, David Acuna, Sanja Fidler
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.
no code implementations • 1 Jan 2021 • David Acuna, Guojun Zhang, Marc T Law, Sanja Fidler
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.
no code implementations • 16 Feb 2021 • Jonathan Lorraine, David Acuna, Paul Vicol, David Duvenaud
We generalize gradient descent with momentum for optimization in differentiable games to have complex-valued momentum.
no code implementations • NeurIPS 2021 • David Acuna, Jonah Philion, Sanja Fidler
Alternative solutions seek to exploit driving simulators that can generate large amounts of labeled data with a plethora of content variations.
no code implementations • 20 Jan 2022 • Or Litany, Haggai Maron, David Acuna, Jan Kautz, Gal Chechik, Sanja Fidler
Standard Federated Learning (FL) techniques are limited to clients with identical network architectures.
no code implementations • ICLR 2022 • David Acuna, Marc T Law, Guojun Zhang, Sanja Fidler
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.
no code implementations • NeurIPS 2021 • Tianshi Cao, Sasha Doubov, David Acuna, Sanja Fidler
NDS uses a mixture of experts trained on data sources to estimate similarity between each source and the downstream task.
no code implementations • CVPR 2022 • Rafid Mahmood, James Lucas, David Acuna, Daiqing Li, Jonah Philion, Jose M. Alvarez, Zhiding Yu, Sanja Fidler, Marc T. Law
Given a small training data set and a learning algorithm, how much more data is necessary to reach a target validation or test performance?
no code implementations • 19 Aug 2022 • Zian Wang, Wenzheng Chen, David Acuna, Jan Kautz, Sanja Fidler
In this work, we propose a neural approach that estimates the 5D HDR light field from a single image, and a differentiable object insertion formulation that enables end-to-end training with image-based losses that encourage realism.
no code implementations • 9 Feb 2023 • Viraj Prabhu, David Acuna, Andrew Liao, Rafid Mahmood, Marc T. Law, Judy Hoffman, Sanja Fidler, James Lucas
Sim2Real domain adaptation (DA) research focuses on the constrained setting of adapting from a labeled synthetic source domain to an unlabeled or sparsely labeled real target domain.
no code implementations • ICCV 2023 • Daiqing Li, Huan Ling, Amlan Kar, David Acuna, Seung Wook Kim, Karsten Kreis, Antonio Torralba, Sanja Fidler
In this work, we introduce a self-supervised feature representation learning framework DreamTeacher that utilizes generative networks for pre-training downstream image backbones.
no code implementations • 9 Apr 2024 • Yuan-Hong Liao, Rafid Mahmood, Sanja Fidler, David Acuna
We find that if prompted appropriately, VLMs can utilize feedback both in a single step and iteratively, showcasing the potential of feedback as an alternative technique to improve grounding in internet-scale VLMs.
no code implementations • 16 Apr 2024 • Ashkan Mirzaei, Riccardo de Lutio, Seung Wook Kim, David Acuna, Jonathan Kelly, Sanja Fidler, Igor Gilitschenski, Zan Gojcic
In this work, we propose an approach for 3D scene inpainting -- the task of coherently replacing parts of the reconstructed scene with desired content.