Related papers: BitMar: Low-Bit Multimodal Fusion with Episodic Me…

Transformer networks have emerged as the state-of-the-art approach for natural language processing tasks and are gaining popularity in other domains such as computer vision and audio processing. However, the efficient hardware acceleration…

The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in…

Due to the high price and heavy energy consumption of GPUs, deploying deep models on IoT devices such as microcontrollers makes significant contributions for ecological AI. Conventional methods successfully enable convolutional neural…

Vision Transformer and its variants have demonstrated great potential in various computer vision tasks. But conventional vision transformers often focus on global dependency at a coarse level, which suffer from a learning challenge on…

This paper presents the Sensorimotor Transformer (SMT), a vision model inspired by human saccadic eye movements that prioritize high-saliency regions in visual input to enhance computational efficiency and reduce memory consumption. Unlike…

Scene text recognition has attracted particular research interest because it is a very challenging problem and has various applications. The most cutting-edge methods are attentional encoder-decoder frameworks that learn the alignment…

Computing-in-Memory (CIM) macros have gained popularity for deep learning acceleration due to their highly parallel computation and low power consumption. However, limited macro size and ADC precision introduce throughput and accuracy…

While the multi-branch architecture is one of the key ingredients to the success of computer vision tasks, it has not been well investigated in natural language processing, especially sequence learning tasks. In this work, we propose a…

Diffusion Transformers (DiTs) achieve state-of-the-art video generation quality, but their substantial memory and computational footprints hinder edge deployment. Quantization can reduce these costs, yet existing methods often degrade video…

Referring video object segmentation aims to segment the object referred by a given language expression. Existing works typically require compressed video bitstream to be decoded to RGB frames before being segmented, which increases…

Objective: Transformers, born to remedy the inadequate receptive fields of CNNs, have drawn explosive attention recently. However, the daunting computational complexity of global representation learning, together with rigid window…

Eye movement (EM) is a new highly secure biometric behavioral modality that has received increasing attention in recent years. Although deep neural networks, such as convolutional neural network (CNN), have recently achieved promising…

Recent works have demonstrated that transformer can achieve promising performance in computer vision, by exploiting the relationship among image patches with self-attention. While they only consider the attention in a single feature layer,…

Even if Application-Specific Integrated Circuits (ASIC) have proven to be a relevant choice for integrating inference at the edge, they are often limited in terms of applicability. In this paper, we demonstrate that an ASIC neural network…

Recent deep multi-view stereo (MVS) methods have widely incorporated transformers into cascade network for high-resolution depth estimation, achieving impressive results. However, existing transformer-based methods are constrained by their…

Transformers have made great progress in dealing with computer vision tasks. However, existing vision transformers do not yet possess the ability of building the interactions among features of different scales, which is perceptually…

Recently, Transformer-based methods have achieved impressive results in single image super-resolution (SISR). However, the lack of locality mechanism and high complexity limit their application in the field of super-resolution (SR). To…

Transformers have become the cornerstone of modern large-scale language models, but their reliance on softmax attention poses a computational bottleneck at both training and inference. Recurrent models offer high efficiency, but compressing…

Vision Transformers (ViTs) have shown significant promise in computer vision applications. However, their performance in few-shot learning is limited by challenges in refining token-level interactions, struggling with limited training data,…

Efficient transformer variants with linear time complexity have been developed to mitigate the quadratic computational overhead of the vanilla transformer. Among them are low-rank projection methods such as Linformer and kernel-based…