Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detection
Current semi-supervised object detection (SSOD) algorithms typically assume class balanced datasets (PASCAL VOC etc.) or slightly class imbalanced datasets (MS-COCO, etc). This assumption can be easily violated since real world datasets can be extremely class imbalanced in nature, thus making the performance of semi-supervised object detectors far from satisfactory. Besides, the research for this problem in SSOD is severely under-explored. To bridge this research gap, we comprehensively study the class imbalance problem for SSOD under more challenging scenarios, thus forming the first experimental setting for class imbalanced SSOD (CI-SSOD). Moreover, we propose a simple yet effective gradient-based sampling framework that tackles the class imbalance problem from the perspective of two types of confirmation biases. To tackle confirmation bias towards majority classes, the gradient-based reweighting and gradient-based thresholding modules leverage the gradients from each class to fully balance the influence of the majority and minority classes. To tackle the confirmation bias from incorrect pseudo labels of minority classes, the class-rebalancing sampling module resamples unlabeled data following the guidance of the gradient-based reweighting module. Experiments on three proposed sub-tasks, namely MS-COCO, MS-COCO to Object365 and LVIS, suggest that our method outperforms current class imbalanced object detectors by clear margins, serving as a baseline for future research in CI-SSOD. Code will be available at https://github.com/nightkeepers/CI-SSOD.
Code (1)
Tasks
object-detectionObject DetectionSemi-Supervised Object DetectionSimilar Papers 제목 키워드 기반
Balanced Semi-Supervised Generative Adversarial Network for Damage Assessment from Low-Data Imbalanced-Class Regime
In recent years, applying deep learning (DL) to assess structural damages has gained growing popularity in vision-based structural health monitoring (SHM). However, both data deficiency and class-imbalance hinder the wid…
Generative Adversarial NetworkStructural Health MonitoringTransfer LearningIterative Nearest Neighborhood Oversampling in Semisupervised Learning from Imbalanced Data
Transductive graph-based semi-supervised learning methods usually build an undirected graph utilizing both labeled and unlabeled samples as vertices. Those methods propagate label information of labeled samples to neighb…
General Classificationimbalanced classificationClass-Level Confidence Based 3D Semi-Supervised Learning
Recent state-of-the-art method FlexMatch firstly demonstrated that correctly estimating learning status is crucial for semi-supervised learning (SSL). However, the estimation method proposed by FlexMatch does not take in…
Weakly Supervised-Based Oversampling for High Imbalance and High Dimensionality Data Classification
With the abundance of industrial datasets, imbalanced classification has become a common problem in several application domains. Oversampling is an effective method to solve imbalanced classification. One of the main cha…
ClassificationGeneral Classificationimbalanced classificationVocal Bursts Intensity Prediction+1Exploiting Synthetically Generated Data with Semi-Supervised Learning for Small and Imbalanced Datasets
Data augmentation is rapidly gaining attention in machine learning. Synthetic data can be generated by simple transformations or through the data distribution. In the latter case, the main challenge is to estimate the la…
Binary ClassificationData AugmentationGeneral Classification