Related papers: An Analysis of Pre-Training on Object Detection

Recent results indicate that the generic descriptors extracted from the convolutional neural networks are very powerful. This paper adds to the mounting evidence that this is indeed the case. We report on a series of experiments conducted…

Object detection has been expanded from a limited number of categories to open vocabulary. Moving forward, a complete intelligent vision system requires understanding more fine-grained object descriptions, object parts. In this paper, we…

The use of pretrained deep neural networks represents an attractive way to achieve strong results with few data available. When specialized in dense problems such as object detection, learning local rather than global information in images…

Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…

Most object detectors contain two important components: a feature extractor and an object classifier. The feature extractor has rapidly evolved with significant research efforts leading to better deep convolutional architectures. The object…

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…

State-of-the-art visual perception models for a wide range of tasks rely on supervised pretraining. ImageNet classification is the de facto pretraining task for these models. Yet, ImageNet is now nearly ten years old and is by modern…

Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This is because the object activation maps are trained with the…

Data augmentation is a critical component of training deep learning models. Although data augmentation has been shown to significantly improve image classification, its potential has not been thoroughly investigated for object detection.…

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…

Image retrieval in realistic scenarios targets large dynamic datasets of unlabeled images. In these cases, training or fine-tuning a model every time new images are added to the database is neither efficient nor scalable. Convolutional…

This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a large, unlabeled image collection, we extract random pairs of patches from each image…

Comparing to deep neural networks trained for specific tasks, those foundational deep networks trained on generic datasets such as ImageNet classification, benefits from larger-scale datasets, simpler network structure and easier training…

This paper addresses the challenge of establishing a bridge between deep convolutional neural networks and conventional object detection frameworks for accurate and efficient generic object detection. We introduce Dense Neural Patterns,…

In this paper, we introduce a fully convolutional network for the document layout analysis task. While state-of-the-art methods are using models pre-trained on natural scene images, our method Doc-UFCN relies on a U-shaped model trained…

Pre-training models on large scale datasets, like ImageNet, is a standard practice in computer vision. This paradigm is especially effective for tasks with small training sets, for which high-capacity models tend to overfit. In this work,…

The field of object detection has made significant advances riding on the wave of region-based ConvNets, but their training procedure still includes many heuristics and hyperparameters that are costly to tune. We present a simple yet…

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…

Self-supervised pre-training, based on the pretext task of instance discrimination, has fueled the recent advance in label-efficient object detection. However, existing studies focus on pre-training only a feature extractor network to learn…

Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable…