The proposed model then warps the input frames, depth maps, and contextual features based on the optical flow and local interpolation kernels for synthesizing the output frame.
To achieve this result, we first train an EfficientNet model on labeled ImageNet images and use it as a teacher to generate pseudo labels on 300M unlabeled images.
SOTA for Image Classification on ImageNet (using extra training data)
Moving forward, we will work on unlocking stage-2 optimizations, with up to 8x memory savings per device, and ultimately stage-3 optimizations, reducing memory linearly with respect to the number of devices and potentially scaling to models of arbitrary size.
In this paper, we first study a principled layerwise adaptation strategy to accelerate training of deep neural networks using large mini-batches.
#9 best model for Question Answering on SQuAD1.1 dev (F1 metric)
Data-driven approaches, most prominently deep learning, have become powerful tools for prediction in many domains.
3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications.
Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks.
SOTA for Natural Language Inference on QNLI