263 citations · 811 across the 52 of their papers we have counts for
15 papers · 1 filter
High-Throughput Synchronous Deep RL
Iou-Jen Liu, Raymond A. Yeh, Alexander G. Schwing
Deep reinforcement learning (RL) is computationally demanding and requires processing of many data points. Synchronous methods enjoy training stability while having lower data thro…
Towards a Better Global Loss Landscape of GANs
Ruoyu Sun, Tiantian Fang, Alex Schwing
Understanding of GAN training is still very limited. One major challenge is its non-convex-non-concave min-max objective, which may lead to sub-optimal local minima. In this work,…
UFO: A Unified Framework towards Omni-supervised Object Detection
Zhongzheng Ren, Zhiding Yu, Xiaodong Yang +3
Existing work on object detection often relies on a single form of annotation: the model is trained using either accurate yet costly bounding boxes or cheaper but less expressive i…
Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies
Itai Gat, Idan Schwartz, Alexander Schwing +1
Many recent datasets contain a variety of different data modalities, for instance, image, question, and answer data in visual question answering (VQA). When training deep net class…
A Contrastive Learning Approach for Training Variational Autoencoder Priors
Jyoti Aneja, Alexander Schwing, Jan Kautz +1
Variational autoencoders (VAEs) are one of the powerful likelihood-based generative models with applications in many domains. However, they struggle to generate high-quality images…
A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks
Unnat Jain, Luca Weihs, Eric Kolve +4
Autonomous agents must learn to collaborate. It is not scalable to develop a new centralized agent every time a task's difficulty outpaces a single agent's abilities. While multi-a…