Interpolation-based semi-supervised learning for object detection

Abstract

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).

References in corpus (16)

• Improved Regularization of Convolutional Neural Networks with Cutout
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• DSSD : Deconvolutional Single Shot Detector
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Temporal Ensembling for Semi-Supervised Learning
• Interpolation Consistency Training for Semi-Supervised Learning
• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
• Manifold Mixup: Better Representations by Interpolating Hidden States
• Bag of Freebies for Training Object Detection Neural Networks
• Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer
• Enhancement of SSD by concatenating feature maps for object detection
• Weakly- and Semi-Supervised Object Detection with Expectation-Maximization Algorithm
• On Adversarial Mixup Resynthesis
• Collaborative Learning for Weakly Supervised Object Detection
• Mixup Regularization for Region Proposal based Object Detectors
• Tell Me What They're Holding: Weakly-supervised Object Detection with Transferable Knowledge from Human-object Interaction

Cited by in corpus (4)

• Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework
• Towards Domain-Agnostic Contrastive Learning
• Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection
• Pseudo-Labeling Enhanced by Privileged Information and Its Application to In Situ Sequencing Images