CVPR 2019 We propose Task-Aware Feature Embedding Networks (TAFE-Nets) to learn how to adapt the image representation to a new task in a meta learning fashion.
CVPR 2019 We propose Hierarchical Discrete Distribution Decomposition (HD^3), a framework suitable for learning probabilistic pixel correspondences in both optical flow and stereo matching.
ICRA 2019 We propose a driving policy learning framework that predicts feature representations of future visual inputs.
ICRA 2019 We show that object-centric models outperform object-agnostic methods in scenes with other vehicles and pedestrians.
ECCV 2018 We introduce SkipNet, a modified residual network, that uses a gating network to selectively skip convolutional blocks based on the activations of the previous layer.
Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation
ECCV 2018 We aim to characterize adversarial examples based on spatial context information in semantic segmentation.
UAI 2018 We introduce the “I Don’t Know” (IDK) prediction cascades framework to accelerate inference without a loss in prediction accuracy.
CVPR 2018 Oral We augment standard architectures with deeper aggregation to better fuse information across layers.
CVPR 2018 Spotlight We develop a local texture loss in addition to adversarial and content loss to train the generative network.
CVPR 2018 We introduce an automatic method for editing a portrait photo so that the subject appears to be wearing makeup in the style of another person in a reference photo.
3DV 2017 We propose using a generative adversarial network (GAN) to assist a novice user in designing real-world shapes with a simple interface.
CVPR 2017 We show that dilated residual networks (DRNs) outperform their non-dilated counterparts in image classification without increasing the model’s depth or complexity.
CVPR 2017 Oral We develop an end-to-end trainable architecture for learning to predict a distribution over future vehicle egomotion from instantaneous monocular camera observations and previous vehicle state.
CVPR 2017 We propose a deep adversarial image synthesis architecture that is conditioned on sketched boundaries and sparse color strokes to generate realistic images.
CVPR 2017 Oral Our network uses a dilation-based 3D context module to efficiently expand the receptive field and enable 3D context learning.
3DOR 2017 This track provides a benchmark to evaluate large-scale 3D shape retrieval based on the ShapeNet dataset.
arXiv 2016 We introduce the first domain adaptive semantic segmentation method, proposing an unsupervised adversarial approach to pixel prediction problems.
Siggraph 2016 We seek a relative quality measure within a series of photos taken of the same scene, which can be used for automatic photo triage.
ICLR 2016 We study dilated convolution in depth. It has become a foundamental network operation.
arXiv 2015 We propose to amplify human effort through a partially automated labeling scheme, leveraging deep learning with humans in the loop.
CVPR 2015 We propose an automatic algorithm for global alignment of LiDAR data collected with Google Street View cars in urban environments.
CVPR 2015 Oral We propose to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid.
arXiv 2015 We present ShapeNet: a richly-annotated, large-scale repository of shapes represented by 3D CAD models of objects.
CVPR 2014 We have discovered that 3D reconstruction can be achieved from a single still photographic capture due to accidental motions of the photographer.