相关论文: Using MLIR Transform to Design Sliced Convolution …

In clinical practice, medical image analysis often requires efficient execution on resource-constrained mobile devices. However, existing mobile models-primarily optimized for natural images-tend to perform poorly on medical tasks due to…

Convolution neural networks (CNNs) and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL). Most of the current studies on MTL solely rely on CNN or Transformer. In this…

Depth completion, which aims to generate high-quality dense depth maps from sparse depth maps, has attracted increasing attention in recent years. Previous work usually employs RGB images as guidance, and introduces iterative spatial…

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…

Recently, deep learning has made remarkable strides, especially with generative modeling, such as large language models and probabilistic diffusion models. However, training these models often involves significant computational resources,…

Traditional deep learning methods in medical imaging often focus solely on segmentation or classification, limiting their ability to leverage shared information. Multi-task learning (MTL) addresses this by combining both tasks through…

In recent years, neural networks have surpassed classical algorithms in areas such as object recognition, e.g. in the well-known ImageNet challenge. As a result, great effort is being put into developing fast and efficient accelerators,…

MLIR has become popular since it was open sourced in 2019. A sub-project of LLVM, the flexibility provided by MLIR to represent Intermediate Representations (IR) as dialects at different abstraction levels, to mix these, and to leverage…

A new technique is proposed for fault-tolerant linear, sesquilinear and bijective (LSB) operations on $M$ integer data streams ($M\geq3$), such as: scaling, additions/subtractions, inner or outer vector products, permutations and…

Convolution is a compute-intensive operation placed at the heart of Convolution Neural Networks (CNNs). It has led to the development of many high-performance algorithms, such as Im2col-GEMM, Winograd, and Direct-Convolution. However, the…

Transposed convolution is crucial for generating high-resolution outputs, yet has received little attention compared to convolution layers. In this work we revisit transposed convolution and introduce a novel layer that allows us to place…

One of the practical choices for making a lightweight semantic segmentation model is to combine a depth-wise separable convolution with a dilated convolution. However, the simple combination of these two methods results in an…

Recently, Transformers have emerged as the go-to architecture for both vision and language modeling tasks, but their computational efficiency is limited by the length of the input sequence. To address this, several efficient variants of…

We initiate the first empirical study on the use of MLP architectures for vision-and-language (VL) fusion. Through extensive experiments on 5 VL tasks and 5 robust VQA benchmarks, we find that: (i) Without pre-training, using MLPs for…

To compete with existing mobile architectures, MobileViG introduces Sparse Vision Graph Attention (SVGA), a fast token-mixing operator based on the principles of GNNs. However, MobileViG scales poorly with model size, falling at most 1%…

We introduce LLaVA-MoD, a novel framework designed to enable the efficient training of small-scale Multimodal Language Models (s-MLLM) by distilling knowledge from large-scale MLLM (l-MLLM). Our approach tackles two fundamental challenges…

Transformer-based methods have achieved impressive image restoration performance due to their capacities to model long-range dependency compared to CNN-based methods. However, advances like SwinIR adopts the window-based and local attention…

Rotation invariance is essential for precise, object-level segmentation in UAV aerial imagery, where targets can have arbitrary orientations and exhibit fine-scale details. Conventional segmentation architectures like U-Net rely on…

This paper focuses on the recently introduced Successive Cancellation Flip (SCFlip) decoder of polar codes. Our contribution is twofold. First, we propose the use of an optimized metric to determine the flipping positions within the SCFlip…

Convolutional neural network (CNN) based methods have achieved great successes in medical image segmentation, but their capability to learn global representations is still limited due to using small effective receptive fields of convolution…