Search Results for author:
Found 4 papers, 0 papers with code
HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction
Concretely, we introduce a hybrid representation called HIQuery to represent all map elements, and propose a point-element interactor to interactively extract and encode the hybrid information of elements, e. g. point position and element shape, into the HIQuery.
Object-Centric Multi-Task Learning for Human Instances
Human is one of the most essential classes in visual recognition tasks such as detection, segmentation, and pose estimation.
RaScaNet: Learning Tiny Models by Raster-Scanning Images
RaScaNet reads only a few rows of pixels at a time using a convolutional neural network and then sequentially learns the representation of the whole image using a recurrent neural network.
Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss
We demonstrate the effectiveness of our trainable quantizer on ImageNet dataset with various network architectures such as ResNet-18, -34 and AlexNet, on which it outperforms existing methods to achieve the state-of-the-art accuracy.
