相关论文: CycleMLP: A MLP-like Architecture for Dense Predic…

This paper presents an improved DETR detector that maintains a "plain" nature: using a single-scale feature map and global cross-attention calculations without specific locality constraints, in contrast to previous leading DETR-based…

The Transformer architecture has dominated machine learning in a wide range of tasks. The specific characteristic of this architecture is an expensive scaled dot-product attention mechanism that models the inter-token interactions, which is…

Recently the dense Simultaneous Localization and Mapping (SLAM) based on neural implicit representation has shown impressive progress in hole filling and high-fidelity mapping. Nevertheless, existing methods either heavily rely on known…

A distinctive representation of image patches in form of features is a key component of many computer vision and robotics tasks, such as image matching, image retrieval, and visual localization. State-of-the-art descriptors, from…

Time series forecasting is a fundamental tool with wide ranging applications, yet recent debates question whether complex nonlinear architectures truly outperform simple linear models. Prior claims of dominance of the linear model often…

FPN (Feature Pyramid Network) has become a basic component of most SoTA one stage object detectors. Many previous studies have repeatedly proved that FPN can caputre better multi-scale feature maps to more precisely describe objects if they…

Transformers are a widespread and successful model architecture, particularly in Natural Language Processing (NLP) and Computer Vision (CV). The essential innovation of this architecture is the Attention Mechanism, which solves the problem…

Whole-slide image analysis via the means of computational pathology often relies on processing tessellated gigapixel images with only slide-level labels available. Applying multiple instance learning-based methods or transformer models is…

Deep learning has become the state-of-the-art approach to medical tomographic imaging. A common approach is to feed the result of a simple inversion, for example the backprojection, to a multiscale convolutional neural network (CNN) which…

We present a system using Multimodal LLMs (MLLMs) to analyze a large database with tens of millions of images captured at different times, with the aim of discovering patterns in temporal changes. Specifically, we aim to capture frequent…

Although using convolutional neural networks (CNNs) as backbones achieves great successes in computer vision, this work investigates a simple backbone network useful for many dense prediction tasks without convolutions. Unlike the…

In this work, we propose a balanced multi-component and multi-layer neural network (MMNN) structure to accurately and efficiently approximate functions with complex features, in terms of both degrees of freedom and computational cost. The…

In this paper, we address the problem of detecting small, dense, and overlapping objects, a major challenge in computer vision. Our focus is on reviewing proposed methods based on deep learning supervised approaches. We provide a detailed…

Multimodal large language models (MLLMs) have demonstrated impressive performance in various vision-language (VL) tasks, but their expensive computations still limit the real-world application. To address this issue, recent efforts aim to…

While machine learning (ML) interatomic potentials (IPs) are able to achieve accuracies nearing the level of noise inherent in the first-principles data to which they are trained, it remains to be shown if their increased complexities are…

In this paper, we aim at automatically searching an efficient network architecture for dense image prediction. Particularly, we follow the encoder-decoder style and focus on designing a connectivity structure for the decoder. To achieve…

Click-through rate (CTR) prediction is one of the fundamental tasks for online advertising and recommendation. While multi-layer perceptron (MLP) serves as a core component in many deep CTR prediction models, it has been widely recognized…

Crowd counting models in highly congested areas confront two main challenges: weak localization ability and difficulty in differentiating between foreground and background, leading to inaccurate estimations. The reason is that objects in…

Large pre-trained language models based on transformer architecture have drastically changed the natural language processing (NLP) landscape. However, deploying those models for on-device applications in constrained devices such as smart…

Compared with 2D MRI, 3D MRI provides superior volumetric spatial resolution and signal-to-noise ratio. However, it is more challenging to reconstruct 3D MRI images. Current methods are mainly based on convolutional neural networks (CNN)…