Related papers: iFormer: Integrating ConvNet and Transformer for M…

Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transformers tend to have larger model capacity, their generalization…

Recently, pure transformer-based models have shown great potentials for vision tasks such as image classification and detection. However, the design of transformer networks is challenging. It has been observed that the depth, embedding…

Local feature matching is a computationally intensive task at the subpixel level. While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-based methods with a sequential extract-to-match pipeline,…

Transformers are a popular choice for classification tasks and as backbones for object detection tasks. However, their high latency brings challenges in their adaptation to lightweight object detection systems. We present an approximation…

Both Convolutional Neural Networks (CNNs) and Transformers have shown great success in semantic segmentation tasks. Efforts have been made to integrate CNNs with Transformer models to capture both local and global context interactions.…

Convolutional Neural networks (CNN) have been the first choice of paradigm in many computer vision applications. The convolution operation however has a significant weakness which is it only operates on a local neighborhood of pixels, thus…

Local feature matching between images remains a challenging task, especially in the presence of significant appearance variations, e.g., extreme viewpoint changes. In this work, we propose DeepMatcher, a deep Transformer-based network built…

Balancing accuracy and latency on high-resolution images is a critical challenge for lightweight models, particularly for Transformer-based architectures that often suffer from excessive latency. To address this issue, we introduce…

The portrait matting task aims to extract an alpha matte with complete semantics and finely-detailed contours. In comparison to CNN-based approaches, transformers with self-attention module have a better capacity to capture long-range…

Transformer and its variants have shown great potential for various vision tasks in recent years, including image classification, object detection and segmentation. Meanwhile, recent studies also reveal that with proper architecture design,…

There is a growing trend to outsource the inference task of large transformer models to cloud servers. However, this poses a severe threat to users' private data as they are exposed to cloud servers after uploading. Although several works…

In this paper, we present DevFormer, a novel transformer-based architecture for addressing the complex and computationally demanding problem of hardware design optimization. Despite the demonstrated efficacy of transformers in domains…

Transformers have been extensively studied in medical image segmentation to build pairwise long-range dependence. Yet, relatively limited well-annotated medical image data makes transformers struggle to extract diverse global features,…

In this paper, we introduce \texttt{IAFormer}, a novel Transformer-based architecture that efficiently integrates pairwise particle interactions through a dynamic sparse attention mechanism. \texttt{IAFormer} has two new mechanisms within…

Transformers have captured growing attention in computer vision, thanks to its large capacity and global processing capabilities. However, transformers are data hungry, and their ability to generalize is constrained compared to…

Understanding indoor scenes is crucial for urban studies. Considering the dynamic nature of indoor environments, effective semantic segmentation requires both real-time operation and high accuracy.To address this, we propose AsymFormer, a…

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…

This paper introduces FaceLiVT, a lightweight yet powerful face recognition model that integrates a hybrid Convolution Neural Network (CNN)-Transformer architecture with an innovative and lightweight Multi-Head Linear Attention (MHLA)…

Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in modeling the long-range…

This article presents Appformer, a novel mobile application prediction framework inspired by the efficiency of Transformer-like architectures in processing sequential data through self-attention mechanisms. Combining a Multi-Modal Data…