相关论文: Beyond MACs: Hardware Efficient Architecture Desig…

Transformers have shown significant effectiveness for various vision tasks including both high-level vision and low-level vision. Recently, masked autoencoders (MAE) for feature pre-training have further unleashed the potential of…

Edge computing must be capable of executing computationally intensive algorithms, such as Deep Neural Networks (DNNs) while operating within a constrained computational resource budget. Such computations involve Matrix Vector…

Currently, lightweight hybrid backbone networks have partially alleviated the issue of computational saturation, but the imbalance in computational efficiencys between convolutional neural networks (CNNs) and attention mechanisms is…

Modern vision models must capture image-level context without sacrificing local detail while remaining computationally affordable. We revisit this tradeoff and advance a simple principle: decouple the roles of global reasoning and local…

Semantic segmentation assigns labels to pixels in images, a critical yet challenging task in computer vision. Convolutional methods, although capturing local dependencies well, struggle with long-range relationships. Vision Transformers…

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…

Transformer, as an alternative to CNN, has been proven effective in many modalities (e.g., texts and images). For 3D point cloud transformers, existing efforts focus primarily on pushing their accuracy to the state-of-the-art level.…

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…

Visual object tracking often employs a multi-stage pipeline of feature extraction, target information integration, and bounding box estimation. To simplify this pipeline and unify the process of feature extraction and target information…

Monocular depth estimation (MDE) plays a pivotal role in various computer vision applications, such as robotics, augmented reality, and autonomous driving. Despite recent advancements, existing methods often fail to meet key requirements…

Many mission-critical systems are based on GPU for inference. It requires not only high recognition accuracy but also low latency in responding time. Although many studies are devoted to optimizing the structure of deep models for efficient…

Mobile edge computing (MEC) is considered as an efficient method to relieve the computation burden of mobile devices. In order to reduce the energy consumption and time delay of mobile devices (MDs) in MEC, multiple users multiple input and…

Deep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations. That is highly inefficient…

MetaFormer, the abstracted architecture of Transformer, has been found to play a significant role in achieving competitive performance. In this paper, we further explore the capacity of MetaFormer, again, without focusing on token mixer…

Computer vision researchers are embracing two promising paradigms: Vision Transformers (ViTs) and Multi-task Learning (MTL), which both show great performance but are computation-intensive, given the quadratic complexity of self-attention…

Cross-attention transformers and other multimodal vision-language models excel at grounding and generation; however, their extensive, full-precision backbones make it challenging to deploy them on edge devices. Memory-augmented…

One of the most pressing challenges prevalent in the steel manufacturing industry is the identification of surface defects. Early identification of casting defects can help boost performance, including streamlining production processes.…

We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder with a 32x compression ratio, which significantly reduces the…

Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison,…

Mobile edge computing (MEC) is an emerging communication scheme that aims at reducing latency. In this paper, we investigate a green MEC system under the existence of an eavesdropper. We use computation efficiency, which is defined as the…