paper-with-me

Papers

Interpolation-based semi-supervised learning for object detection

2020-06-03 · CVPR 2021 1 · Jisoo Jeong, Vikas Verma, Minsung Hyun, Juho Kannala, Nojun Kwak

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).

📄 PDF Abstract BibTeX arXiv:2006.02158

Code (1)

soo89/ISD-SSD pytorch

Tasks

Objectobject-detectionObject Detection

Similar Papers 제목 키워드 기반

MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection

2021-11-22 · Jongmok Kim, Jooyoung Jang, Seunghyeon Seo, Jisoo Jeong 외

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 Detection

MUM: Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection

2022-01-01 · CVPR 2022 1 · Jongmok Kim, Jooyoung Jang, Seunghyeon Seo, Jisoo Jeong 외

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 Detection

Multi-Objective Interpolation Training for Robustness to Label Noise

2020-12-08 · CVPR 2021 1 · Diego Ortego, Eric Arazo, Paul Albert, Noel E. O'Connor 외

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+1

Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training

2022-06-17 · CVPR 2022 1 · Xiao Lu, Yihong Cao, Sheng Liu, Chengjiang Long 외

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 Detection

Hypergraph $p$-Laplacian equations for data interpolation and semi-supervised learning

2024-11-19 · Kehan Shi, Martin Burger

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…