相关论文: Bag of Freebies for Training Object Detection Neur…

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…

Although two-stage object detectors have continuously advanced the state-of-the-art performance in recent years, the training process itself is far from crystal. In this work, we first point out the inconsistency problem between the fixed…

Recently, many researchers have attempted to improve deep learning-based object detection models, both in terms of accuracy and operational speeds. However, frequently, there is a trade-off between speed and accuracy of such models, which…

ImageNet pre-training has been regarded as essential for training accurate object detectors for a long time. Recently, it has been shown that object detectors trained from randomly initialized weights can be on par with those fine-tuned…

Finetuning from a pretrained deep model is found to yield state-of-the-art performance for many vision tasks. This paper investigates many factors that influence the performance in finetuning for object detection. There is a long-tailed…

Model compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a…

Object detection is a crucial component in autonomous vehicle systems. It enables the vehicle to perceive and understand its environment by identifying and locating various objects around it. By utilizing advanced imaging and deep learning…

A common practice in transfer learning is to initialize the downstream model weights by pre-training on a data-abundant upstream task. In object detection specifically, the feature backbone is typically initialized with Imagenet classifier…

Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods. In the literature, however, most refinements are either…

In this paper, we propose a general and efficient pre-training paradigm, Montage pre-training, for object detection. Montage pre-training needs only the target detection dataset while taking only 1/4 computational resources compared to the…

Recent observations have advanced our understanding of the neural network optimization landscape, revealing the existence of (1) paths of high accuracy containing diverse solutions and (2) wider minima offering improved performance.…

We investigate the utility of different auxiliary objectives and training strategies within a neural sequence labeling approach to error detection in learner writing. Auxiliary costs provide the model with additional linguistic information,…

Usually, Neural Networks models are trained with a large dataset of images in homogeneous backgrounds. The issue is that the performance of the network models trained could be significantly degraded in a complex and heterogeneous…

Machine Learning facilitates building a large variety of models, starting from elementary linear regression models to very complex neural networks. Neural networks are currently limited by the size of data provided and the huge…

The convolutional neural networks (CNNs) trained on ILSVRC12 ImageNet were the backbone of various applications as a generic classifier, a feature extractor or a base model for transfer learning. This paper describes automated heuristics…

Existing computer vision and object detection methods strongly rely on neural networks and deep learning. This active research area is used for applications such as autonomous driving, aerial photography, protection, and monitoring.…

While recent deep neural networks have achieved a promising performance on object recognition, they rely implicitly on the visual contents of the whole image. In this paper, we train deep neural net- works on the foreground (object) and…

The ImageNet pre-training initialization is the de-facto standard for object detection. He et al. found it is possible to train detector from scratch(random initialization) while needing a longer training schedule with proper normalization…

Although accuracy and other common metrics can provide a useful window into the performance of an object detection model, they lack a deeper view of the model's decision process. Regardless of the quality of the training data and process,…

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) pre-training on a large-scale dataset and (2) finetuning on the target dataset. This strategy helps reduce dependence on the target dataset and…