Interpolation-based semi-supervised learning for object detection
Despite the data labeling cost for the object detection tasks being substantially more than that of the classification tasks, semi-supervised learning methods for object detection have not been studied much. In this paper, we propose an Interpolation-based Semi-supervised learning method for object Detection (ISD), which considers and solves the problems caused by applying conventional Interpolation Regularization (IR) directly to object detection. We divide the output of the model into two types according to the objectness scores of both original patches that are mixed in IR. Then, we apply a separate loss suitable for each type in an unsupervised manner. The proposed losses dramatically improve the performance of semi-supervised learning as well as supervised learning. In the supervised learning setting, our method improves the baseline methods by a significant margin. In the semi-supervised learning setting, our algorithm improves the performance on a benchmark dataset (PASCAL VOC and MSCOCO) in a benchmark architecture (SSD).
Code (1)
Tasks
Objectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection
Many recent semi-supervised learning (SSL) studies build teacher-student architecture and train the student network by the generated supervisory signal from the teacher. Data augmentation strategy plays a significant rol…
Data Augmentationobject-detectionObject DetectionSemi-Supervised Object DetectionMUM: Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection
Many recent semi-supervised learning (SSL) studies build teacher-student architecture and train the student network by the generated supervisory signal from the teacher. Data augmentation strategy plays a significant…
Data Augmentationobject-detectionObject DetectionSemi-Supervised Object DetectionMulti-Objective Interpolation Training for Robustness to Label Noise
Deep neural networks trained with standard cross-entropy loss memorize noisy labels, which degrades their performance. Most research to mitigate this memorization proposes new robust classification loss functions. Conver…
Contrastive LearningImage ClassificationMemorizationRepresentation Learning+1Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training
It is challenging to annotate large-scale datasets for supervised video shadow detection methods. Using a model trained on labeled images to the video frames directly may lead to high generalization error and temporal in…
Shadow DetectionSpatial InterpolationVideo Shadow DetectionHypergraph $p$-Laplacian equations for data interpolation and semi-supervised learning
Hypergraph learning with $p$-Laplacian regularization has attracted a lot of attention due to its flexibility in modeling higher-order relationships in data. This paper focuses on its fast numerical implementation, which…