Related papers: Designing BERT for Convolutional Networks: Sparse …
Generally, convolutional neural networks (CNNs) process data on a regular grid, e.g. data generated by ordinary cameras. Designing CNNs for sparse and irregularly spaced input data is still an open research problem with numerous…
We present a network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice. Naively applying convolutions on this lattice scales…
We frame the task of predicting a semantic labeling as a sparse reconstruction procedure that applies a target-specific learned transfer function to a generic deep sparse code representation of an image. This strategy partitions training…
Material classification in natural settings is a challenge due to complex interplay of geometry, reflectance properties, and illumination. Previous work on material classification relies strongly on hand-engineered features of visual…
Hyperspectral imaging systems collect and process information from specific wavelengths across the electromagnetic spectrum. The fusion of multi-spectral bands in the visible spectrum has been exploited to improve face recognition…
The availability of large-scale annotated image datasets and recent advances in supervised deep learning methods enable the end-to-end derivation of representative image features that can impact a variety of image analysis problems. Such…
Pruning large neural networks to create high-quality, independently trainable sparse masks, which can maintain similar performance to their dense counterparts, is very desirable due to the reduced space and time complexity. As research…
Deep Convolutional Neural Networks (DCNN) require millions of labeled training examples for image classification and object detection tasks, which restrict these models to domains where such datasets are available. In this paper, we explore…
Due to the current lack of large-scale datasets at the million-scale level, tasks involving panoramic images predominantly rely on existing two-dimensional pre-trained image benchmark models as backbone networks. However, these networks are…
We propose a new approach for 3D instance segmentation based on sparse convolution and point affinity prediction, which indicates the likelihood of two points belonging to the same instance. The proposed network, built upon submanifold…
Transformer-based pre-trained language models, such as BERT, achieve great success in various natural language understanding tasks. Prior research found that BERT captures a rich hierarchy of linguistic information at different layers.…
Convolutional Sparse Coding (CSC) is a well-established image representation model especially suited for image restoration tasks. In this work, we extend the applicability of this model by proposing a supervised approach to convolutional…
Image fusion is a significant problem in many fields including digital photography, computational imaging and remote sensing, to name but a few. Recently, deep learning has emerged as an important tool for image fusion. This paper presents…
This paper tackles the challenging problem of hyperspectral (HS) image denoising. Unlike existing deep learning-based methods usually adopting complicated network architectures or empirically stacking off-the-shelf modules to pursue…
Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large…
We consider the optimization of deep convolutional neural networks (CNNs) such that they provide good performance while having reduced complexity if deployed on either conventional systems with spatial-domain convolution or lower-complexity…
Recently, deep learning methods such as the convolutional neural networks have gained prominence in the area of image denoising. This is owing to their proven ability to surpass state-of-the-art classical image denoising algorithms such as…
Neural networks, specifically deep convolutional neural networks, have achieved unprecedented performance in various computer vision tasks, but the rationale for the computations and structures of successful neural networks is not fully…
The convolution operation is a central building block of neural network architectures widely used in computer vision. The size of the convolution kernels determines both the expressiveness of convolutional neural networks (CNN), as well as…
Objective: X-ray computed tomography employing sparse projection views has emerged as a contemporary technique to mitigate radiation dose. However, due to the inadequate number of projection views, an analytic reconstruction method…