相关论文: How to Train an Accurate and Efficient Object Dete…

The paradigm of large-scale pre-training followed by downstream fine-tuning has been widely employed in various object detection algorithms. In this paper, we reveal discrepancies in data, model, and task between the pre-training and…

An object detector's ability to detect and flag \textit{novel} objects during open-world deployments is critical for many real-world applications. Unfortunately, much of the work in open object detection today is disjointed and fails to…

Open-set detection is crucial for robust UAV autonomy in air-to-air object detection under real-world conditions. Traditional closed-set detectors degrade significantly under domain shifts and flight data corruption, posing risks to…

Vision Transformers (ViTs) dominate self-supervised learning (SSL). While they have proven highly effective for large-scale pretraining, they are computationally inefficient and scale poorly with image size. Consequently, foundational…

In this paper, we want to show the potential benefit of a dynamic auto-tuning approach for the inference process in the Deep Neural Network (DNN) context, tackling the object detection challenge. We benchmarked different neural networks to…

In the era of data-centric AI, the ability to curate high-quality training data is as crucial as model design. Coresets offer a principled approach to data reduction, enabling efficient learning on large datasets through importance…

How can we segment varying numbers of objects where each specific object represents its own separate class? To make the problem even more realistic, how can we add and delete classes on the fly without retraining or fine-tuning? This is the…

Crowdsourced 3D CAD models are becoming easily accessible online, and can potentially generate an infinite number of training images for almost any object category.We show that augmenting the training data of contemporary Deep Convolutional…

Deep learning methods typically require vast amounts of training data to reach their full potential. While some publicly available datasets exists, domain specific data always needs to be collected and manually labeled, an expensive, time…

In this paper, we present a novel paradigm to enhance the ability of object detector, e.g., expanding categories or improving detection performance, by training on synthetic dataset generated from diffusion models. Specifically, we…

Object-centric understanding is fundamental to human vision and required for complex reasoning. Traditional methods define slot-based bottlenecks to learn object properties explicitly, while recent self-supervised vision models like DINO…

In this paper, we propose an original object detection methodology applied to Global Wheat Head Detection (GWHD) Dataset. We have been through two major architectures of object detection which are FasterRCNN and EfficientDet, in order to…

Transformers have been widely used in numerous vision problems especially for visual recognition and detection. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the…

This paper presents a new approach for training two-stage object detection ensemble models, more specifically, Faster R-CNN models to estimate uncertainty. We propose training one Region Proposal Network(RPN) and multiple Fast R-CNN…

Object detection and instance recognition play a central role in many AI applications like autonomous driving, video surveillance and medical image analysis. However, training object detection models on large scale datasets remains…

Uncertainty estimation is crucial in safety-critical settings such as automated driving as it provides valuable information for several downstream tasks including high-level decision making and path planning. In this work, we propose…

We propose a new approach, Synthetic Optimized Layout with Instance Detection (SOLID), to pretrain object detectors with synthetic images. Our "SOLID" approach consists of two main components: (1) generating synthetic images using a…

In this study, a novel deep learning algorithm for object detection, named MelNet, was introduced. MelNet underwent training utilizing the KITTI dataset for object detection. Following 300 training epochs, MelNet attained an mAP (mean…

Dataset pruning -- selecting a small yet informative subset of training data -- has emerged as a promising strategy for efficient machine learning, offering significant reductions in computational cost and storage compared to alternatives…

The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly.…