Related papers: Data-Centric Debugging: mitigating model failures …

Deep neural networks (DNN) have achieved remarkable success in various fields, including computer vision and natural language processing. However, training an effective DNN model still poses challenges. This paper aims to propose a method…

Deep neural networks have become a foundational tool for addressing imaging inverse problems. They are typically trained for a specific task, with a supervised loss to learn a mapping from the observations to the image to recover. However,…

Major advancements in computer vision can primarily be attributed to the use of labeled datasets. However, acquiring labels for datasets often results in errors which can harm model performance. Recent works have proposed methods to…

Training and deploying deepfake detection models on edge devices offers the advantage of maintaining data privacy and confidentiality by processing it close to its source. However, this approach is constrained by the limited computational…

Deep neural networks (DNNs) often suffer from "catastrophic forgetting" during incremental learning (IL) --- an abrupt degradation of performance on the original set of classes when the training objective is adapted to a newly added set of…

Content-based image retrieval is the process of retrieving a subset of images from an extensive image gallery based on visual contents, such as color, shape or spatial relations, and texture. In some applications, such as localization,…

Current network training paradigms primarily focus on either centralized or decentralized data regimes. However, in practice, data availability often exhibits a hybrid nature, where both regimes coexist. This hybrid setting presents new…

Deep convolutional neural networks have shown remarkable results on multiple detection tasks. Despite the significant progress, the performance of such detectors are often assessed in public benchmarks under non-realistic conditions.…

Real-time CNN-based object detection models for applications like surveillance can achieve high accuracy but are computationally expensive. Recent works have shown 10 to 100x reduction in computation cost for inference by using…

Designing neural network architectures is a challenging task and knowing which specific layers of a model must be adapted to improve the performance is almost a mystery. In this paper, we introduce a novel theory and metric to identify…

Edge nodes are crucial for detection against multitudes of cyber attacks on Internet-of-Things endpoints and is set to become part of a multi-billion industry. The resource constraints in this novel network infrastructure tier constricts…

Deep neural networks trained end-to-end to map a measurement of a (noisy) image to a clean image perform excellent for a variety of linear inverse problems. Current methods are only trained on a few hundreds or thousands of images as…

The performance of deep neural networks is strongly influenced by the training dataset setup. In particular, when attributes having a strong correlation with the target attribute are present, the trained model can provide unintended…

Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy,…

Ensembles of Convolutional neural networks have shown remarkable results in learning discriminative semantic features for image classification tasks. Though, the models in the ensemble often concentrate on similar regions in images. This…

In this paper, we introduced the novel concept of advisor network to address the problem of noisy labels in image classification. Deep neural networks (DNN) are prone to performance reduction and overfitting problems on training data with…

Image compression is a widely used technique to reduce the spatial redundancy in images. Recently, learning based image compression has achieved significant progress by using the powerful representation ability from neural networks.…

Constructing fine-grained image datasets typically requires domain-specific expert knowledge, which is not always available for crowd-sourcing platform annotators. Accordingly, learning directly from web images becomes an alternative method…

Deep neural networks have established as a powerful tool for large scale supervised classification tasks. The state-of-the-art performances of deep neural networks are conditioned to the availability of large number of accurately labeled…

Image denoising is a classical problem in low level computer vision. Model-based optimization methods and deep learning approaches have been the two main strategies for solving the problem. Model-based optimization methods are flexible for…