Related papers: Focal Loss for Dense Object Detection

Deep learning has been widely recognized as a promising approach in different computer vision applications. Specifically, one-stage object detector and two-stage object detector are regarded as the most important two groups of Convolutional…

Most of object detection algorithms can be categorized into two classes: two-stage detectors and one-stage detectors. Recently, many efforts have been devoted to one-stage detectors for the simple yet effective architecture. Different from…

Object detection is an important task in computer vision which serves a lot of real-world applications such as autonomous driving, surveillance and robotics. Along with the rapid thrive of large-scale data, numerous state-of-the-art…

RetinaNet proposed Focal Loss for classification task and improved one-stage detectors greatly. However, there is still a gap between it and two-stage detectors. We analyze the prediction of RetinaNet and find that the misalignment of…

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This…

Real-time single-stage object detectors based on deep learning still remain less accurate than more complex ones. The trade-off between model performance and computational speed is a major challenge. In this paper, we propose a new way to…

Recent CNN based object detectors, no matter one-stage methods like YOLO, SSD, and RetinaNe or two-stage detectors like Faster R-CNN, R-FCN and FPN are usually trying to directly finetune from ImageNet pre-trained models designed for image…

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This…

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…

Despite the recent success of long-tailed object detection, almost all long-tailed object detectors are developed based on the two-stage paradigm. In practice, one-stage detectors are more prevalent in the industry because they have a…

Automated driving object detection has always been a challenging task in computer vision due to environmental uncertainties. These uncertainties include significant differences in object sizes and encountering the class unseen. It may…

Deep learning has revolutionized object detection thanks to large-scale datasets, but their object categories are still arguably very limited. In this paper, we attempt to enrich such categories by addressing the one-shot object detection…

3D object detection is still an open problem in autonomous driving scenes. When recognizing and localizing key objects from sparse 3D inputs, autonomous vehicles suffer from a larger continuous searching space and higher fore-background…

Compared with model architectures, the training process, which is also crucial to the success of detectors, has received relatively less attention in object detection. In this work, we carefully revisit the standard training practice of…

Few-shot object detection, which aims at detecting novel objects rapidly from extremely few annotated examples of previously unseen classes, has attracted significant research interest in the community. Most existing approaches employ the…

Recent object detection models require large amounts of annotated data for training a new classes of objects. Few-shot object detection (FSOD) aims to address this problem by learning novel classes given only a few samples. While…

Detecting the objects in dense and rotated scenes is a challenging task. Recent works on this topic are mostly based on Faster RCNN or Retinanet. As they are highly dependent on the pre-set dense anchors and the NMS operation, the approach…

Most existing object detectors suffer from class imbalance problems that hinder balanced performance. In particular, anchor free object detectors have to solve the background imbalance problem due to detection in a per-pixel prediction…

Recent researches attempt to improve the detection performance by adopting the idea of cascade for single-stage detectors. In this paper, we analyze and discover that inconsistency is the major factor limiting the performance. The refined…

DETR is a recently proposed Transformer-based method which views object detection as a set prediction problem and achieves state-of-the-art performance but demands extra-long training time to converge. In this paper, we investigate the…