• Home
  • Search
  • Semi-Supervised Few-Shot Object Detection via Adaptive Pseudo Labeling
  • Cite Icon34
  • https://doi.org/10.1109/tcsvt.2023.3301854Copy DOI Icon

Semi-Supervised Few-Shot Object Detection via Adaptive Pseudo Labeling

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Few-shot object detection (FSOD) aims to detect novel objects with limited annotated examples. Mainstream methods suffer from the data scarcity of novel classes with insufficient intra-class variations, which makes the trained model biased to base classes. Actually, there are massive unlabeled novel instances in the base dataset and their adequate utilization will enhance the discriminability of model to novel classes. This paper proposes a semi-supervised few-shot object detection method, which utilizes a teacher model and a pre-trained few-shot object detector to guide the learning of a student model through adaptive pseudo labeling. In particular, a class-adaptive threshold filtering (CATF) strategy is designed to deal with the class-imbalance problem of pseudo labels. And for each novel class, the threshold to select valuable pseudo labels is determined by quantile statistics of the confidence score distribution of pseudo labels. Furthermore, the pre-trained detector and the teacher model are associated with the preliminary CATF and in-depth CATF, respectively, and then the pseudo labels from the two-stream CATF are fused to provide supervisions. In this way, the knowledge of these two models is exploited, which improves the quality of pseudo labels. Under these supervisions, the student model is trained and the teacher model is correspondingly updated through parameters sharing, thus forming a positive feedback to improve the performance of both models. Besides, an attention module is integrated to the teacher and student models to enhance the feature representation of novel instances. The validations on PASCAL VOC and MS COCO show the effectiveness of the proposed method.

Similar Papers
  • PDF
  • Research Article
  • Citations5

Improving Object Detection Accuracy with Self-Training Based on Bi-Directional Pseudo Label Recovery

  • Jun 07, 2024
  • Electronics
  • Shoaib Sajid +3
  • Research Article
  • Citations1

Semantic contrast with uncertainty-aware pseudo label for lumbar semi-supervised classification

  • Jun 15, 2024
  • Computers in Biology and Medicine
  • Jinjin Hai +6
  • Conference Article
  • Citations5

Online pseudo labeling for polyp segmentation with momentum networks

  • Oct 19, 2022
  • Toan Pham Van +5
  • Research Article
  • Citations5

Consistency-guided pseudo labeling for transductive zero-shot learning

  • Apr 10, 2024
  • Information Sciences
  • Hairui Yang +4
  • Research Article
  • Citations13

Source-free domain adaptation via dynamic pseudo labeling and Self-supervision

  • Jul 22, 2024
  • Pattern Recognition
  • Qiankun Ma +7
  • Conference Article
  • Citations10

Adaptive Pseudo Labeling for Source-Free Domain Adaptation in Medical Image Segmentation

  • May 23, 2022
  • Chen Li +4
  • Research Article
  • Citations16

Semi-supervised domain generalization with evolving intermediate domain

  • Jan 12, 2024
  • Pattern Recognition
  • Luojun Lin +6
  • Book Chapter
  • Citations10

Semi-supervised Medical Image Classification with Temporal Knowledge-Aware Regularization

  • Jan 01, 2022
  • Qiushi Yang +4
  • Conference Article
  • Citations20

Refined Pseudo Labeling for Source-Free Domain Adaptive Object Detection

  • Jun 04, 2023
  • Siqi Zhang +2
  • Conference Article
  • Citations114

Semi-supervised Semantic Segmentation with Error Localization Network

  • Jun 01, 2022
  • Donghyeon Kwon +1
  • Research Article
  • Citations1

Pseudo Labeling Collaborative Embedding Representation: A Multi-Channel GCNs Framework for Semi-Supervised Node Classification

  • Jan 01, 2024
  • IEEE Access
  • Mengnan Pang +3
  • Research Article
  • Citations23

Growth threshold for pseudo labeling and pseudo label dropout for semi-supervised medical image classification

  • Dec 27, 2023
  • Engineering Applications of Artificial Intelligence
  • Shaofeng Zhou +6
  • Research Article
  • Citations1

CoNPL: Consistency training framework with noise-aware pseudo labeling for dense pose estimation

  • Jul 10, 2024
  • Image and Vision Computing
  • Jiaxiao Wen +3
  • Conference Article
  • Citations236

Contrastive Test-Time Adaptation

  • Jun 01, 2022
  • Dian Chen +3
  • Research Article
  • Citations17

Exploring Feature Representation Learning for Semi-Supervised Medical Image Segmentation.

  • Nov 01, 2024
  • IEEE transactions on neural networks and learning systems
  • Huimin Wu +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.