activity
20152024
most citedYou Only Need Adversarial Supervision for Semantic Image Synthesis

70 citations · 231 across the 35 of their papers we have counts for

collaborators
Showing 2022Show all

13 papers · 1 filter

cs.CV2022

Discovering Class-Specific GAN Controls for Semantic Image Synthesis

Edgar Schönfeld, Julio Borges, Vadim Sushko +2

Prior work has extensively studied the latent space structure of GANs for unconditional image synthesis, enabling global editing of generated images by the unsupervised discovery o…

cs.CV20225 cited

Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts

Qi Fan, Mattia Segu, Yu-Wing Tai +4

Improving model's generalizability against domain shifts is crucial, especially for safety-critical applications such as autonomous driving. Real-world domain styles can vary subst…

cs.CV2022

Leveraging Self-Supervised Training for Unintentional Action Recognition

Enea Duka, Anna Kukleva, Bernt Schiele

Unintentional actions are rare occurrences that are difficult to define precisely and that are highly dependent on the temporal context of the action. In this work, we explore such…

cs.CV20222 cited

TeST: Test-time Self-Training under Distribution Shift

Samarth Sinha, Peter Gehler, Francesco Locatello +1

Despite their recent success, deep neural networks continue to perform poorly when they encounter distribution shifts at test time. Many recently proposed approaches try to counter…

cs.CV202211 cited

MTR-A: 1st Place Solution for 2022 Waymo Open Dataset Challenge -- Motion Prediction

Shaoshuai Shi, Li Jiang, Dengxin Dai +1

In this report, we present the 1st place solution for motion prediction track in 2022 Waymo Open Dataset Challenges. We propose a novel Motion Transformer framework for multimodal…

cs.CV20221 cited

ComplETR: Reducing the cost of annotations for object detection in dense scenes with vision transformers

Achin Jain, Kibok Lee, Gurumurthy Swaminathan +4

Annotating bounding boxes for object detection is expensive, time-consuming, and error-prone. In this work, we propose a DETR based framework called ComplETR that is designed to ex…