Related papers: MONET: Modeling and Optimization of neural NEtwork…

While deep neural networks have achieved state-of-the-art performance across a large number of complex tasks, it remains a big challenge to deploy such networks for practical, on-device edge scenarios such as on mobile devices, consumer…

We introduce a model-based image reconstruction framework with a convolution neural network (CNN) based regularization prior. The proposed formulation provides a systematic approach for deriving deep architectures for inverse problems with…

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…

Deep neural networks can achieve great successes when presented with large data sets and sufficient computational resources. However, their ability to learn new concepts quickly is limited. Meta-learning is one approach to address this…

Edge detection is a long-standing problem in computer vision. Despite the efficiency of existing algorithms, their performance, however, rely heavily on the pre-trained weights of the backbone network on the ImageNet dataset. The use of…

Recognizing human actions from point cloud sequence has attracted tremendous attention from both academia and industry due to its wide applications. However, most previous studies on point cloud action recognition typically require complex…

Deep learning has achieved state-of-the-art accuracies on several computer vision tasks. However, the computational and energy requirements associated with training such deep neural networks can be quite high. In this paper, we propose a…

Fine-tuning models on edge devices like mobile phones would enable privacy-preserving personalization over sensitive data. However, edge training has historically been limited to relatively small models with simple architectures because…

Mixture-of-Expert (MoE) models outperform conventional models by selectively activating different subnets, named experts, on a per-token basis. This gated computation generates dynamic communications that cannot be determined beforehand,…

Over the past decade, deep neural networks have demonstrated significant success using the training scheme that involves mini-batch stochastic gradient descent on extensive datasets. Expanding upon this accomplishment, there has been a…

High-resolution remote sensing imagery increasingly contains dense clusters of tiny objects, the detection of which is extremely challenging due to severe mutual occlusion and limited pixel footprints. Existing detection methods typically…

Network simulation is pivotal in network modeling, assisting with tasks ranging from capacity planning to performance estimation. Traditional approaches such as Discrete Event Simulation (DES) face limitations in terms of computational cost…

Most existing deep neural networks are static, which means they can only do inference at a fixed complexity. But the resource budget can vary substantially across different devices. Even on a single device, the affordable budget can change…

We present here, a novel network architecture called MergeNet for discovering small obstacles for on-road scenes in the context of autonomous driving. The basis of the architecture rests on the central consideration of training with less…

Within the domain of medical image analysis, three distinct methodologies have demonstrated commendable accuracy: Neural Networks, Decision Trees, and Ensemble-Based Learning Algorithms, particularly in the specialized context of genstro…

The diversity of deep learning applications, datasets, and neural network architectures necessitates a careful selection of the architecture and data that match best to a target application. As an attempt to mitigate this dilemma, this…

Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compute linearly during inference. A recent stream of work…

Multiscale modeling is an effective approach for investigating multiphysics systems with largely disparate size features, where models with different resolutions or heterogeneous descriptions are coupled together for predicting the system's…

Incorporating prior knowledge or specifications of input-output relationships into machine learning models has attracted significant attention, as it enhances generalization from limited data and yields conforming outputs. However, most…

Training large text-to-image models requires high-quality, curated datasets with diverse content and detailed captions. Yet the cost and complexity of collecting, filtering, deduplicating, and re-captioning such corpora at scale hinders…