Related papers: LowFormer: Hardware Efficient Design for Convoluti…

Computer vision has become increasingly prevalent in solving real-world problems across diverse domains, including smart agriculture, fishery, and livestock management. These applications may not require processing many image frames per…

In this paper, we introduce the big.LITTLE Vision Transformer, an innovative architecture aimed at achieving efficient visual recognition. This dual-transformer system is composed of two distinct blocks: the big performance block,…

While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares…

Transformers have become the dominant model in natural language processing, owing to their ability to pretrain on massive amounts of data, then transfer to smaller, more specific tasks via fine-tuning. The Vision Transformer was the first…

Entropy estimation is essential for the performance of learned image compression. It has been demonstrated that a transformer-based entropy model is of critical importance for achieving a high compression ratio, however, at the expense of a…

LLM architecture research generally aims to maximize model quality subject to fixed compute/latency budgets. However, many applications of interest such as edge and on-device deployment are further constrained by the model's memory…

State-of-the-art Transformer-based models, with gigantic parameters, are difficult to be accommodated on resource constrained embedded devices. Moreover, with the development of technology, more and more embedded devices are available to…

We present Laneformer, a conceptually simple yet powerful transformer-based architecture tailored for lane detection that is a long-standing research topic for visual perception in autonomous driving. The dominant paradigms rely on purely…

This paper describes a memory-efficient transformer model designed to drive a reduction in memory usage and execution time by substantial orders of magnitude without impairing the model's performance near that of the original model.…

Deep learning techniques have achieved remarkable success in the semantic segmentation of remote sensing images and in land-use change detection. Nevertheless, their real-time deployment on edge platforms remains constrained by decoder…

Massively pre-trained transformer models are computationally expensive to fine-tune, slow for inference, and have large storage requirements. Recent approaches tackle these shortcomings by training smaller models, dynamically reducing the…

Deep learning and Convolutional Neural Networks (CNNs) have driven major transformations in diverse research areas. However, their limitations in handling low-frequency information present obstacles in certain tasks like interpreting global…

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,…

We present WidthFormer, a novel transformer-based module to compute Bird's-Eye-View (BEV) representations from multi-view cameras for real-time autonomous-driving applications. WidthFormer is computationally efficient, robust and does not…

As foundation models become more popular, there is a growing need to efficiently finetune them for downstream tasks. Although numerous adaptation methods have been proposed, they are designed to be efficient only in terms of how many…

Multi-frame depth estimation improves over single-frame approaches by also leveraging geometric relationships between images via feature matching, in addition to learning appearance-based features. In this paper we revisit feature matching…

Transformer models have revolutionized AI tasks, but their large size hinders real-world deployment on resource-constrained and latency-critical edge devices. While binarized Transformers offer a promising solution by significantly reducing…

This paper analyzes the design choices of face detection architecture that improve efficiency of computation cost and accuracy. Specifically, we re-examine the effectiveness of the standard convolutional block as a lightweight backbone…

This paper presents an efficient multi-scale vision Transformer, called ResT, that capably served as a general-purpose backbone for image recognition. Unlike existing Transformer methods, which employ standard Transformer blocks to tackle…

Real-time object detection is crucial for real-world applications as it requires high accuracy with low latency. While Detection Transformers (DETR) have demonstrated significant performance improvements, current real-time DETR models are…