We apply the resulting learned optimizer to a variety of neural network training tasks, where it outperforms the current state of the art learned optimizer -- at matched optimizer computational overhead -- with regard to optimization performance and meta-training speed, and is capable of generalization to tasks far different from those it was meta-trained on.
While deep learning models have replaced hand-designed features across many domains, these models are still trained with hand-designed optimizers.
Diffusion models (DMs) are another class of deep generative models and have recently achieved remarkable performance on various image synthesis tasks.
Ranked #1 on Video Generation on Taichi
Once the subject is embedded in the output domain of the model, the unique identifier can then be used to synthesize fully-novel photorealistic images of the subject contextualized in different scenes.
Generative Adversarial Networks (GANs) are widely adapted for anonymization of human figures.
In this work, we present a conceptually simple and effective method to train a strong bilingual/multilingual multimodal representation model.
We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks.
Ranked #6 on Semantic Segmentation on PASCAL Context
Autonomous agents have made great strides in specialist domains like Atari games and Go.
Salient object detection (SOD) has been in the spotlight recently, yet has been studied less for high-resolution (HR) images.
Ranked #1 on Dichotomous Image Segmentation on DIS-TE4