相关论文: Sliced Recursive Transformer

This paper proposes an efficient hypergraph partitioning framework based on a novel multi-objective non-convex constrained relaxation model. A modified accelerated proximal gradient algorithm is employed to generate diverse $k$-dimensional…

The high computational costs of video super-resolution (VSR) models hinder their deployment on resource-limited devices, (e.g., smartphones and drones). Existing VSR models contain considerable redundant filters, which drag down the…

Pre-trained vision transformers have strong representation benefits to various downstream tasks. Recently, many parameter-efficient fine-tuning (PEFT) methods have been proposed, and their experiments demonstrate that tuning only 1\% extra…

Vision Transformer (ViT), a radically different architecture than convolutional neural networks offers multiple advantages including design simplicity, robustness and state-of-the-art performance on many vision tasks. However, in contrast…

Uniform downsampling remains the de facto standard for reducing spatial resolution in vision backbones. In this work, we propose an alternative design built around a content-aware spatial grouping layer, that dynamically assigns tokens to a…

We propose methodologies to train highly accurate and efficient deep convolutional neural networks (CNNs) for image super resolution (SR). A cascade training approach to deep learning is proposed to improve the accuracy of the neural…

The most recent year has witnessed the success of applying the Vision Transformer (ViT) for image classification. However, there are still evidences indicating that ViT often suffers following two aspects, i) the high computation and the…

In recent years, a great deal of attention has been paid to the Transformer network for speech recognition tasks due to its excellent model performance. However, the Transformer network always involves heavy computation and large number of…

Vision Transformers have been tremendously successful in computer vision tasks. However, their large computational, memory, and energy demands are a challenge for edge inference on FPGAs -- a field that has seen a recent surge in demand. We…

Vision Transformers (ViTs) have emerged as a foundational model in computer vision, excelling in generalization and adaptation to downstream tasks. However, deploying ViTs to support diverse resource constraints typically requires…

Mix-based augmentation has been proven fundamental to the generalization of deep vision models. However, current augmentations only mix samples at the current data batch during training, which ignores the possible knowledge accumulated in…

In this paper we propose a vision system that performs image Super Resolution (SR) with selectivity. Conventional SR techniques, either by multi-image fusion or example-based construction, have failed to capitalize on the intrinsic…

Recently, foundation models based on Vision Transformers (ViTs) have become widely available. However, their fine-tuning process is highly resource-intensive, and it hinders their adoption in several edge or low-energy applications. To this…

Vision transformers (ViTs) have demonstrated great potential in various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. In this paper, we introduce a ternary…

Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sampling. Recent methods reduce cost by compressing width, depth, or sampling steps, but…

Vision transformers (ViTs) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly trained on massive data. However, the computational overhead of…

Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization. Previous compression algorithms usually…

The advent of high-capacity pre-trained models has revolutionized problem-solving in computer vision, shifting the focus from training task-specific models to adapting pre-trained models. Consequently, effectively adapting large pre-trained…

We introduce Elastic Looped Transformers (ELT), a highly parameter-efficient class of visual generative models based on a recurrent transformer architecture. While conventional generative models rely on deep stacks of unique transformer…

Deep Residual Networks have reached the state of the art in many image processing tasks such image classification. However, the cost for a gain in accuracy in terms of depth and memory is prohibitive as it requires a higher number of…