Related papers: Memory Efficient Adaptive Attention For Multiple D…

Owing to flexible architectures of deep convolutional neural networks (CNNs), CNNs are successfully used for image denoising. However, they suffer from the following drawbacks: (i) deep network architecture is very difficult to train. (ii)…

In this work, we present a new, algorithm for multi-domain learning. Given a pretrained architecture and a set of visual domains received sequentially, the goal of multi-domain learning is to produce a single model performing a task in all…

Single-model ensembles (SMEs) have attracted attention as a way to approximate some of the benefits of deep ensembles within a single network. However, under an approximately matched parameter budget, it remains unclear whether model…

Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labeled datasets. However, for video semantic object segmentation, a domain where labels are scarce, effectively…

Unsupervised cross-domain person re-identification (Re-ID) aims to adapt the information from the labelled source domain to an unlabelled target domain. Due to the lack of supervision in the target domain, it is crucial to identify the…

Training Convolutional Neural Networks (CNN) is a resource intensive task that requires specialized hardware for efficient computation. One of the most limiting bottleneck of CNN training is the memory cost associated with storing the…

Despite their success in many computer vision tasks, convolutional networks tend to require large amounts of labeled data to achieve generalization. Furthermore, the performance is not guaranteed on a sample from an unseen domain at test…

Plant diseases serve as one of main threats to food security and crop production. It is thus valuable to exploit recent advances of artificial intelligence to assist plant disease diagnosis. One popular approach is to transform this problem…

A Convolutional Neural Network (CNN) is sometimes confronted with objects of changing appearance ( new instances) that exceed its generalization capability. This requires the CNN to incorporate new knowledge, i.e., to learn incrementally.…

Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily available. To address this issue, we propose a method for…

In recent years, representation learning approaches have disrupted many multimedia computing tasks. Among those approaches, deep convolutional neural networks (CNNs) have notably reached human level expertise on some constrained image…

By redefining the conventional notions of layers, we present an alternative view on finitely wide, fully trainable deep neural networks as stacked linear models in feature spaces, leading to a kernel machine interpretation. Based on this…

Training deep learning based video classifiers for action recognition requires a large amount of labeled videos. The labeling process is labor-intensive and time-consuming. On the other hand, large amount of weakly-labeled images are…

This paper presents an implementation of multilayer feed forward neural networks (NN) to optimize CMOS analog circuits. For modeling and design recently neural network computational modules have got acceptance as an unorthodox and useful…

Convolutional Neural Networks (CNNs) filter the input data using a series of spatial convolution operators with compactly supported stencils and point-wise nonlinearities. Commonly, the convolution operators couple features from all…

End-to-end deep learning improves breast cancer classification on diffusion-weighted MR images (DWI) using a convolutional neural network (CNN) architecture. A limitation of CNN as opposed to previous model-based approaches is the…

The excellent performance of deep neural networks has enabled us to solve several automatization problems, opening an era of autonomous devices. However, current deep net architectures are heavy with millions of parameters and require…

With the tremendous advances in the architecture and scale of convolutional neural networks (CNNs) over the past few decades, they can easily reach or even exceed the performance of humans in certain tasks. However, a recently discovered…

Despite the success of CNN models on a variety of Image classification and segmentation tasks, their extensive computational and storage demands pose considerable challenges for real-world deployment on resource-constrained devices.…

While the deployment of deep learning models on edge devices is increasing, these models often lack robustness when faced with dynamic changes in sensed data. This can be attributed to sensor drift, or variations in the data compared to…