相关论文: EfficientViT: Memory Efficient Vision Transformer …

Vision Transformers have witnessed prevailing success in a series of vision tasks. However, these Transformers often rely on extensive computational costs to achieve high performance, which is burdensome to deploy on resource-constrained…

After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks such as image classification, detection, segmentation, and…

The efficiency of attention is important due to its quadratic time complexity. We enhance the efficiency of attention through two key contributions: First, we leverage the new FP4 Tensor Cores in Blackwell GPUs to accelerate attention…

Learning subtle representation about object parts plays a vital role in fine-grained visual recognition (FGVR) field. The vision transformer (ViT) achieves promising results on computer vision due to its attention mechanism. Nonetheless,…

Vision Transformer (ViT) has made significant advancements in computer vision, thanks to its token mixer's sophisticated ability to capture global dependencies between all tokens. However, the quadratic growth in computational demands as…

Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transformer architectures have been proposed and they show promising…

In recent years, the Vision Transformer (ViT) has garnered significant attention within the computer vision community. However, the core component of ViT, Self-Attention, lacks explicit spatial priors and suffers from quadratic…

Though image transformers have shown competitive results with convolutional neural networks in computer vision tasks, lacking inductive biases such as locality still poses problems in terms of model efficiency especially for embedded…

Recently vision transformer models have become prominent models for a range of vision tasks. These models, however, are usually opaque with weak feature interpretability. Moreover, there is no method currently built for an intrinsically…

Attention for transformers is a critical workload that has recently received significant "attention" as a target for custom acceleration. Yet, while prior work succeeds in reducing attention's memory-bandwidth requirements, it creates load…

As a pioneering work exploring transformer architecture for 3D point cloud understanding, Point Transformer achieves impressive results on multiple highly competitive benchmarks. In this work, we analyze the limitations of the Point…

Transformers have astounding representational power but typically consume considerable computation which is quadratic with image resolution. The prevailing Swin transformer reduces computational costs through a local window strategy.…

Current multimodal large lanauge models possess strong perceptual and reasoning capabilities, however high computational and memory requirements make them difficult to deploy directly on on-device environments. While small-parameter models…

Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi-Head Self-Attention (MHSA) layer still performs a quadratic query-key interaction for every token pair, spending…

Since Transformer has found widespread use in NLP, the potential of Transformer in CV has been realized and has inspired many new approaches. However, the computation required for replacing word tokens with image patches for Transformer…

Recent studies show that Vision Transformers(ViTs) exhibit strong robustness against various corruptions. Although this property is partly attributed to the self-attention mechanism, there is still a lack of systematic understanding. In…

Efficient inference of Multi-Head Latent Attention (MLA) is challenged by deploying the DeepSeek-R1 671B model on a single Multi-GPU server. This paper introduces FlashMLA-ETAP, a novel framework that enhances MLA inference for the…

Vision transformers have shown unprecedented levels of performance in tackling various visual perception tasks in recent years. However, the architectural and computational complexity of such network architectures have made them challenging…

To address the challenges of sensor fusion and safety risk prediction, contemporary closed-loop autonomous driving neural networks leveraging imitation learning typically require a substantial volume of parameters and computational…

While models derived from Vision Transformers (ViTs) have been phonemically surging, pre-trained models cannot seamlessly adapt to arbitrary resolution images without altering the architecture and configuration, such as sampling the…