Related papers: BasisNet: Two-stage Model Synthesis for Efficient …

Multi-scale deep CNN architecture [1, 2, 3] successfully captures both fine and coarse level image descriptors for visual similarity task, but they come up with expensive memory overhead and latency. In this paper, we propose a competing…

Evaluation is essential in image fusion research, yet most existing metrics are directly borrowed from other vision tasks without proper adaptation. These traditional metrics, often based on complex image transformations, not only fail to…

We present a novel, parameter-efficient and practical fully convolutional neural network architecture, termed InfiNet, aimed at voxel-wise semantic segmentation of infant brain MRI images at iso-intense stage, which can be easily extended…

As the ubiquity of deep learning in various machine learning applications has amplified, a proliferation of neural network models has been trained and shared on public model repositories. In the context of a targeted machine learning…

Bayesian Neural Networks (BNNs) provide principled estimates of model and data uncertainty by encoding parameters as distributions. This makes them key enablers for reliable AI that can be deployed on safety critical edge systems. These…

Residual networks (ResNets) represent a powerful type of convolutional neural network (CNN) architecture, widely adopted and used in various tasks. In this work we propose an improved version of ResNets. Our proposed improvements address…

Batch normalization is a key component of most image classification models, but it has many undesirable properties stemming from its dependence on the batch size and interactions between examples. Although recent work has succeeded in…

Dynamic inference is a feasible way to reduce the computational cost of convolutional neural network(CNN), which can dynamically adjust the computation for each input sample. One of the ways to achieve dynamic inference is to use…

Reducing inference time and energy usage while maintaining prediction accuracy has become a significant concern for deep neural networks (DNN) inference on resource-constrained edge devices. To address this problem, we propose a novel…

We present QuickNet, a fast and accurate network architecture that is both faster and significantly more accurate than other fast deep architectures like SqueezeNet. Furthermore, it uses less parameters than previous networks, making it…

Fine-tuning pre-trained foundation models has made significant progress in music information retrieval. However, applying these models to beat tracking tasks remains unexplored as the limited annotated data renders conventional fine-tuning…

We provide a two-way integration for the widely adopted ControlNet by integrating external condition generation algorithms into a single dense prediction method and incorporating its individually trained image generation processes into a…

Mixed-precision quantization, where a deep neural network's layers are quantized to different precisions, offers the opportunity to optimize the trade-offs between model size, latency, and statistical accuracy beyond what can be achieved…

Deep image registration has demonstrated exceptional accuracy and fast inference. Recent advances have adopted either multiple cascades or pyramid architectures to estimate dense deformation fields in a coarse-to-fine manner. However, due…

With the growing adoption of deep learning for on-device TinyML applications, there has been an ever-increasing demand for efficient neural network backbones optimized for the edge. Recently, the introduction of attention condenser networks…

Bayesian neural networks (BNNs) demonstrate promising success in improving the robustness and uncertainty quantification of modern deep learning. However, they generally struggle with underfitting at scale and parameter efficiency. On the…

The large computing and memory cost of deep neural networks (DNNs) often precludes their use in resource-constrained devices. Quantizing the parameters and operations to lower bit-precision offers substantial memory and energy savings for…

We propose Dataset Reinforcement, a strategy to improve a dataset once such that the accuracy of any model architecture trained on the reinforced dataset is improved at no additional training cost for users. We propose a Dataset…

Learning from limited amounts of data is the hallmark of intelligence, requiring strong generalization and abstraction skills. In a machine learning context, data-efficient methods are of high practical importance since data collection and…

A lack of generalizability is one key limitation of deep learning based segmentation. Typically, one manually labels new training images when segmenting organs in different imaging modalities or segmenting abnormal organs from distinct…