Deep Learning
Unfolding Taylor's Approximations for Image Restoration Man Zhou
To solve the above problems, inspired by T aylor's Approximations, we unfold Taylor's Formula to construct a novel framework for image restoration.
Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling
As deep learning blooms with growing demand for computation and data resources, outsourcing model training to a powerful cloud server becomes an attractive alternative to training at a low-power and cost-effective end device.
Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling
As deep learning blooms with growing demand for computation and data resources, outsourcing model training to a powerful cloud server becomes an attractive alternative to training at a low-power and cost-effective end device.
Big Bird: Transformers for Longer Sequences - Appendix A Universal Approximators A.1 Notation
Teaching machines to read and comprehend.
Neural Program Generation Modulo Static Analysis
The root cause of these issues, we believe, is that current neural models of code treat programs as text rather than artifacts that are constructed following a semantics . In principle, a model could learn semantics from syntax given enough data.
Continuous Surface Embeddings
In this work, we focus on the task of learning and representing dense correspondences in deformable object categories. While this problem has been considered before, solutions so far have been rather ad-hoc for specific object types (i.e., humans), often with significant manual work involved. However, scaling the geometry understanding to all objects in nature requires more automated approaches that can also express correspondences between related, but geometrically different objects. To this end, we propose a new, learnable image-based representation of dense correspondences. Our model predicts, for each pixel in a 2D image, an embedding vector of the corresponding vertex in the object mesh, therefore establishing dense correspondences between image pixels and 3D object geometry. We demonstrate that the proposed approach performs on par or better than the state-of-the-art methods for dense pose estimation for humans, while being conceptually simpler. We also collect a new in-the-wild dataset of dense correspondences for animal classes and demonstrate that our framework scales naturally to the new deformable object categories.
Multifaceted Uncertainty Estimation for Label-Efficient Deep Learning
DL based evidence prediction with uncertainty anchor sample identification.
