Related papers: Improving the Resolution of CNN Feature Maps Effic…
Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…
Object segmentation and structure localization are important steps in automated image analysis pipelines for microscopy images. We present a convolution neural network (CNN) based deep learning architecture for segmentation of objects in…
Deep dictionary learning seeks multiple dictionaries at different image scales to capture complementary coherent characteristics. We propose a method for learning a hierarchy of synthesis dictionaries with an image classification goal. The…
In the current era, biometric based access control is becoming more popular due to its simplicity and ease to use by the users. It reduces the manual work of identity recognition and facilitates the automatic processing. The face is one of…
Finding a template in a search image is an important task underlying many computer vision applications. Recent approaches perform template matching in a deep feature-space, produced by a convolutional neural network (CNN), which is found to…
Most existing dehazing algorithms often use hand-crafted features or Convolutional Neural Networks (CNN)-based methods to generate clear images using pixel-level Mean Square Error (MSE) loss. The generated images generally have better…
State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampling path responsible for extracting coarse semantic features,…
Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…
This study aims to optimize the few-shot image classification task and improve the model's feature extraction and classification performance by combining self-supervised learning with the deep network model ResNet-101. During the training…
Several image processing tasks, such as image classification and object detection, have been significantly improved using Convolutional Neural Networks (CNN). Like ResNet and EfficientNet, many architectures have achieved outstanding…
In this paper, we introduce robust and synergetic hand-crafted features and a simple but efficient deep feature from a convolutional neural network (CNN) architecture for defocus estimation. This paper systematically analyzes the…
Object classification is a significant task in computer vision. It has become an effective research area as an important aspect of image processing and the building block of image localization, detection, and scene parsing. Object…
The objective of this paper is the effective transfer of the Convolutional Neural Network (CNN) feature in image search and classification. Systematically, we study three facts in CNN transfer. 1) We demonstrate the advantage of using…
Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks. However, the transition to semantic segmentation is hampered by strict memory…
Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even supercomputers. The number of parameters needed in CNNs, however, are often large and…
Image inpainting has earned substantial progress, owing to the encoder-and-decoder pipeline, which is benefited from the Convolutional Neural Networks (CNNs) with convolutional downsampling to inpaint the masked regions semantically from…
The customizable nature of deep learning models have allowed them to be successful predictors in various disciplines. These models are often trained with respect to thousands or millions of instances for complicated problems, but the…
Instance segmentation of planar regions in indoor scenes benefits visual SLAM and other applications such as augmented reality (AR) where scene understanding is required. Existing methods built upon two-stage frameworks show satisfactory…
CNNs with strong learning abilities are widely chosen to resolve super-resolution problem. However, CNNs depend on deeper network architectures to improve performance of image super-resolution, which may increase computational cost in…
Structured pruning compresses neural networks by reducing channels (filters) for fast inference and low footprint at run-time. To restore accuracy after pruning, fine-tuning is usually applied to pruned networks. However, too few remaining…