Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation

Wu, Jiong; Song, Liangchen; Wang, Tiancai; Zhang, Qian; Yuan, Junsong

doi:10.1145/3394171.3413970

Cited by 76 publications

(48 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Object detection and instance segmentation has attracted increasing attention in the long-tailed learning community [19], [35], [68], [78], [103], [126], [159], [160], where most existing studies are conducted based on LVIS and COCO. In addition to these widelyused benchmarks, many other applications have also been explored, including urban scene understanding [26], [161], unmanned aerial vehicle detection [27], point cloud segmentation [162], [163].…”

Section: Image Detection and Segmentationmentioning

confidence: 99%

Deep Long-Tailed Learning: A Survey

Zhang¹,

Kang²,

Hooi³

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution. In the last decade, deep learning has emerged as a powerful recognition model for learning high-quality image representations and has led to remarkable breakthroughs in generic visual recognition. However, long-tailed class imbalance, a common problem in practical visual recognition tasks, often limits the practicality of deep network based recognition models in real-world applications, since they can be easily biased towards dominant classes and perform poorly on tail classes. To address this problem, a large number of studies have been conducted in recent years, making promising progress in the field of deep long-tailed learning. Considering the rapid evolution of this field, this paper aims to provide a comprehensive survey on recent advances in deep long-tailed learning. To be specific, we group existing deep long-tailed learning studies into three main categories (i.e., class re-balancing, information augmentation and module improvement), and review these methods following this taxonomy in detail. Afterward, we empirically analyze several state-of-the-art methods by evaluating to what extent they address the issue of class imbalance via a newly proposed evaluation metric, i.e., relative accuracy. We conclude the survey by highlighting important applications of deep long-tailed learning and identifying several promising directions for future research.

show abstract

Section: Image Detection and Segmentationmentioning

confidence: 99%

Deep Long-Tailed Learning: A Survey

Zhang¹,

Kang²,

Hooi³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Later on, a series of works tried to alleviate classification bias. One line of works tried to improve the sample strategy [4,10,42], while another major line of works focus on loss engineering. Equalization Loss [32] and its improvements [31] down-weight the negative gradients for tail classes from head classes, while droploss [17] further takes the gradients from background into consideration.…”

Section: Related Workmentioning

confidence: 99%

“…Similarly, ACSL [38] only penalize negative classes over threshold. Separating the categories into some small groups [21,42] and simple calibration [26,47] helps, too. [28,36] modified the original soft-max function by embedding the distribution prior, achieving success.…”

Section: Related Workmentioning

confidence: 99%

Relieving Long-tailed Instance Segmentation via Pairwise Class Balance

He¹,

Zhang²,

Wei³

et al. 2022

Preprint

View full text Add to dashboard Cite

Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. This renders "how to appropriately define and alleviate the bias" one of the most important issues. Prior works mainly use label distribution or mean score information to indicate a coarse-grained bias. In this paper, we explore to excavate the confusion matrix, which carries the fine-grained misclassification details, to relieve the pairwise biases, generalizing the coarse one. To this end, we propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences. PCB generates fightback soft labels for regularization during training. Besides, an iterative learning paradigm is developed to support a progressive and smooth regularization in such debiasing. PCB can be plugged and played to any existing method as a complement. Experimental results on LVIS demonstrate that our method achieves state-of-theart performance without bells and whistles. Superior results across various architectures show the generalization ability.

show abstract

“…Object detection is one of the most fundamental and challenging tasks in computer vision. In recent years, with the development of deep convolutional neural networks (CNN), many high-performance object detectors have been proposed [28,17,26,27,15,31]. In general, the current popular detectors can be divided into two categories: two-Figure 1.…”

Section: Introductionmentioning

confidence: 99%

TS4Net: Two-Stage Sample Selective Strategy for Rotating Object Detection

Feng¹,

Li²,

Han³

et al. 2021

Preprint

View full text Add to dashboard Cite

Rotating object detection has wide applications in aerial photographs, remote sensing images, UAVs, etc. At present, most of the rotating object detection datasets focus on the field of remote sensing, and these images are usually shot in high-altitude scenes. However, image datasets captured at low-altitude areas also should be concerned, such as drone-based datasets. So we present a low-altitude dronebased dataset, named UAV-ROD, aiming to promote the research and development in rotating object detection and UAV applications. The UAV-ROD consists of 1577 images and 30,090 instances of car category annotated by oriented bounding boxes. In particular, The UAV-ROD can be utilized for the rotating object detection, vehicle orientation recognition and object counting tasks. Compared with horizontal object detection, the regression stage of the rotation detection is a tricky problem. In this paper, we propose a rotating object detector TS 4 Net, which contains anchor refinement module (ARM) and two-stage sample selective strategy (TS 4 ). The ARM can convert preseted horizontal anchors into high-quality rotated anchors through twostage anchor refinement. The TS 4 module utilizes different constrained sample selective strategies to allocate positive and negative samples, which is adaptive to the regression task in different stages. Benefiting from the ARM and TS 4 , the TS 4 Net can achieve superior performance for rotating object detection solely with one preseted horizontal anchor. Extensive experimental results on UAV-ROD dataset and three remote sensing datasets DOTA, HRSC2016 and UCAS-AOD demonstrate that our method achieves competitive performance against most state-of-the-art methods.

show abstract

Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation

Cited by 76 publications

References 41 publications

Deep Long-Tailed Learning: A Survey

Deep Long-Tailed Learning: A Survey

Relieving Long-tailed Instance Segmentation via Pairwise Class Balance

TS4Net: Two-Stage Sample Selective Strategy for Rotating Object Detection

Contact Info

Product

Resources

About