Related papers: EDM: Efficient Deep Feature Matching

Feature matching is a challenging computer vision task that involves finding correspondences between two images of a 3D scene. In this paper we consider the dense approach instead of the more common sparse paradigm, thus striving to find…

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency.…

Many DNN-enabled vision applications constantly operate under severe energy constraints such as unmanned aerial vehicles, Augmented Reality headsets, and smartphones. Designing DNNs that can meet a stringent energy budget is becoming…

In industrial inspection and component alignment tasks, template matching requires efficient estimation of a target's position and geometric state (rotation and scaling) under complex backgrounds to support precise downstream operations.…

The recent development of deep learning large models in medicine shows remarkable performance in medical image analysis and diagnosis, but their large number of parameters causes memory and inference latency challenges. Knowledge…

Previous deep image registration methods that employ single homography, multi-grid homography, or thin-plate spline often struggle with real scenes containing depth disparities due to their inherent limitations. To address this, we propose…

In recent years, the development of smart edge computing systems to process information locally is on the rise. Many near-sensor machine learning (ML) approaches have been implemented to introduce accurate and energy efficient template…

Following the rapidly growing digital image usage, automatic image categorization has become preeminent research area. It has broaden and adopted many algorithms from time to time, whereby multi-feature (generally, hand-engineered features)…

This paper introduces a two-phase deep feature calibration framework for efficient learning of semantics enhanced text-image cross-modal joint embedding, which clearly separates the deep feature calibration in data preprocessing from…

High quality AI solutions require joint optimization of AI algorithms and their hardware implementations. In this work, we are the first to propose a fully simultaneous, efficient differentiable DNN architecture and implementation co-search…

The goal of Feature Selection - comprising filter, wrapper, and embedded approaches - is to find the optimal feature subset for designated downstream tasks. Nevertheless, current feature selection methods are limited by: 1) the selection…

Since the BOSS competition, in 2010, most steganalysis approaches use a learning methodology involving two steps: feature extraction, such as the Rich Models (RM), for the image representation, and use of the Ensemble Classifier (EC) for…

This paper introduces a novel feature detector based only on information embedded inside a CNN trained on standard tasks (e.g. classification). While previous works already show that the features of a trained CNN are suitable descriptors,…

Establishing a sparse set of keypoint correspon dences between images is a fundamental task in many computer vision pipelines. Often, this translates into a computationally expensive nearest neighbor search, where every keypoint descriptor…

Edge nodes are crucial for detection against multitudes of cyber attacks on Internet-of-Things endpoints and is set to become part of a multi-billion industry. The resource constraints in this novel network infrastructure tier constricts…

Deep neural networks have evolved as the leading approach in 3D medical image segmentation due to their outstanding performance. However, the ever-increasing model size and computation cost of deep neural networks have become the primary…

We propose Deep Estimators of Features (DEFs), a learning-based framework for predicting sharp geometric features in sampled 3D shapes. Differently from existing data-driven methods, which reduce this problem to feature classification, we…

In this study we present how to approach the problem of building efficient detectors for spectrally efficient frequency division multiplexing (SEFDM) systems. The superiority of residual convolution neural networks (CNNs) for these types of…

Handling varying computational resources is a critical issue in modern AI applications. Adaptive deep networks, featuring the dynamic employment of multiple classifier heads among different layers, have been proposed to address…

Educational data mining (EDM) is a new growing research area and the essence of data mining concepts are used in the educational field for the purpose of extracting useful information on the behaviors of students in the learning process. In…