Related papers: FFConv: Fast Factorized Convolutional Neural Netwo…
The lossy compression techniques produce various artifacts like blurring, distortion at block bounders, ringing and contouring effects on outputs especially at low bit rates. To reduce those compression artifacts various Convolutional…
Convolutional neural networks (CNN) are increasingly used in many areas of computer vision. They are particularly attractive because of their ability to "absorb" great quantities of labeled data through millions of parameters. However, as…
Fully Homomorphic Encryption (FHE) allows computing on encrypted data, enabling secure offloading of computation to untrusted serves. Though it provides ideal security, FHE is expensive when executed in software, 4 to 5 orders of magnitude…
Convolutional neural networks (CNNs) have constantly achieved better performance over years by introducing more complex topology, and enlarging the capacity towards deeper and wider CNNs. This makes the manual design of CNNs extremely…
Deep Convolutional Neural Networks (CNNs) for image classification successively alternate convolutions and downsampling operations, such as pooling layers or strided convolutions, resulting in lower resolution features the deeper the…
Federated learning (FL) enables a loose set of participating clients to collaboratively learn a global model via coordination by a central server and with no need for data sharing. Existing FL approaches that rely on complex algorithms with…
Sequence model based NLP applications can be large. Yet, many applications that benefit from them run on small devices with very limited compute and storage capabilities, while still having run-time constraints. As a result, there is a need…
Deep learning and Convolutional Neural Network (CNN) have becoming increasingly more popular and important in both academic and industrial areas in recent years cause they are able to provide better accuracy and result in classification,…
Deploying Convolutional Neural Network (CNN) models on ubiquitous Internet of Things (IoT) devices in a cloud-assisted manner to provide users with a variety of high-quality services has become mainstream. Most existing studies speed up…
Transformer inference in machine-learning-as-a-service (MLaaS) raises privacy concerns for sensitive user inputs. Prior secure solutions that combine fully homomorphic encryption (FHE) and secure multiparty computation (MPC) are…
Deep Convolutional Neural Networks have become a Swiss knife in solving critical artificial intelligence tasks. However, deploying deep CNN models for latency-critical tasks remains to be challenging because of the complex nature of CNNs.…
Most image denoising networks apply a single set of static convolutional kernels across the entire input image. This is sub-optimal for natural images, as they often consist of heterogeneous visual patterns. Dynamic convolution tries to…
A novel energy-efficient edge computing paradigm is proposed for real-time deep learning-based image upsampling applications. State-of-the-art deep learning solutions for image upsampling are currently trained using either resize or…
Group convolution works well with many deep convolutional neural networks (CNNs) that can effectively compress the model by reducing the number of parameters and computational cost. Using this operation, feature maps of different group…
In order to handle modern convolutional neural networks (CNNs) efficiently, a hardware architecture of CNN inference accelerator is proposed to handle depthwise convolutions and regular convolutions, which are both essential building blocks…
Fully Homomorphic Encryption (FHE) is a set of powerful cryptographic schemes that allows computation to be performed directly on encrypted data with an unlimited depth. Despite FHE's promising in privacy-preserving computing, yet in most…
SVD-based Low-rank compression reduces transformer parameters and nominal FLOPs, but these savings often translate poorly into real LLM serving speedups. We show that this gap is largely a runtime problem: factorized checkpoints fragment…
The convolutional neural network (CNN) is one of the most commonly used architectures for computer vision tasks. The key building block of a CNN is the convolutional kernel that aggregates information from the pixel neighborhood and shares…
Generative large language models (LLMs) have revolutionized multiple domains. Modern LLMs predominantly rely on an autoregressive decoding strategy, which generates output tokens sequentially and employs a key-value cache (KV cache) to…
Tensor decomposition is one of the fundamental technique for model compression of deep convolution neural networks owing to its ability to reveal the latent relations among complex structures. However, most existing methods compress the…