Related papers: Single image calibration using knowledge distillat…
We propose a new method for creating computationally efficient convolutional neural networks (CNNs) by using low-rank representations of convolutional filters. Rather than approximating filters in previously-trained networks with more…
Recently, convolutional neural networks (CNNs) have shown great success on the task of monocular depth estimation. A fundamental yet unanswered question is: how CNNs can infer depth from a single image. Toward answering this question, we…
Fine-grained image labels are desirable for many computer vision applications, such as visual search or mobile AI assistant. These applications rely on image classification models that can produce hundreds of thousands (e.g. 100K) of…
Convolutional Neural Networks (CNNs) are a standard approach for visual recognition due to their capacity to learn hierarchical representations from raw pixels. In practice, practitioners often choose among (i) training a compact custom CNN…
Multi-scale approach has been used for blind image / video deblurring problems to yield excellent performance for both conventional and recent deep-learning-based state-of-the-art methods. Bicubic down-sampling is a typical choice for…
This paper proposes to go beyond the state-of-the-art deep convolutional neural network (CNN) by incorporating the information from object detection, focusing on dealing with fine-grained image classification. Unfortunately, CNN suffers…
Image segmentation is considered to be one of the critical tasks in hyperspectral remote sensing image processing. Recently, convolutional neural network (CNN) has established itself as a powerful model in segmentation and classification by…
It is challenging to remove rain-steaks from a single rainy image because the rain steaks are spatially varying in the rainy image. Although the CNN based methods have reported promising performance recently, there are still some defects,…
In this work, we propose a camera self-calibration algorithm for generic cameras with arbitrary non-linear distortions. We jointly learn the geometry of the scene and the accurate camera parameters without any calibration objects. Our…
Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added…
This paper addresses the problem of depth estimation from a single still image. Inspired by recent works on multi- scale convolutional neural networks (CNN), we propose a deep model which fuses complementary information derived from…
One impressive advantage of convolutional neural networks (CNNs) is their ability to automatically learn feature representation from raw pixels, eliminating the need for hand-designed procedures. However, recent methods for single image…
Recently, there is a vast interest in developing image feature learning methods that are independent of the training data, such as deep image prior, InGAN, SinGAN, and DCIL. These methods are unsupervised and are used to perform low-level…
We propose the first general framework to automatically correct different types of geometric distortion in a single input image. Our proposed method employs convolutional neural networks (CNNs) trained by using a large synthetic distortion…
In this paper, we propose a novel online self-calibration approach for Light Detection and Ranging (LiDAR) and camera sensors. Compared to the previous CNN-based methods that concatenate the feature maps of the RGB image and decalibrated…
Convolutional Neural Networks (CNNs) have achieved remarkable success across a wide range of machine learning tasks by leveraging hierarchical feature learning through deep architectures. However, the large number of layers and millions of…
Deep Convolutional Neural Networks (CNN) have exhibited superior performance in many visual recognition tasks including image classification, object detection, and scene label- ing, due to their large learning capacity and resistance to…
Continual learning is an emerging topic in the field of deep learning, where a model is expected to learn continuously for new upcoming tasks without forgetting previous experiences. This field has witnessed numerous advancements, but few…
Although deep convolutional neural networks (CNNs) have achieved great success in computer vision tasks, its real-world application is still impeded by its voracious demand of computational resources. Current works mostly seek to compress…
Conventional 2D Convolutional Neural Networks (CNN) extract features from an input image by applying linear filters. These filters compute the spatial coherence by weighting the photometric information on a fixed neighborhood without taking…