Guided Distillation for Semi-Supervised Instance Segmentation

• URL: http://arxiv.org/abs/2308.02668v2
• Date: Thu, 14 Dec 2023 10:57:38 GMT
• Title: Guided Distillation for Semi-Supervised Instance Segmentation
• Authors: Tariq Berrada, Camille Couprie, Karteek Alahari, Jakob Verbeek
• Abstract summary: We present novel design choices to significantly improve teacher-student distillation models. In particular, we improve the distillation approach by introducing a novel "guided burn-in" stage. Contrary to previous work which uses only supervised data for the burn-in period of the student model, we also use guidance of the teacher model to exploit unlabeled data in the burn-in period.
• Score: 29.688029979801577
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although instance segmentation methods have improved considerably, the dominant paradigm is to rely on fully-annotated training images, which are tedious to obtain. To alleviate this reliance, and boost results, semi-supervised approaches leverage unlabeled data as an additional training signal that limits overfitting to the labeled samples. In this context, we present novel design choices to significantly improve teacher-student distillation models. In particular, we (i) improve the distillation approach by introducing a novel "guided burn-in" stage, and (ii) evaluate different instance segmentation architectures, as well as backbone networks and pre-training strategies. Contrary to previous work which uses only supervised data for the burn-in period of the student model, we also use guidance of the teacher model to exploit unlabeled data in the burn-in period. Our improved distillation approach leads to substantial improvements over previous state-of-the-art results. For example, on the Cityscapes dataset we improve mask-AP from 23.7 to 33.9 when using labels for 10\% of images, and on the COCO dataset we improve mask-AP from 18.3 to 34.1 when using labels for only 1\% of the training data.

Related papers

• Weakly Contrastive Learning via Batch Instance Discrimination and Feature Clustering for Small Sample SAR ATR [7.2932563202952725]
  We propose a novel framework named Batch Instance Discrimination and Feature Clustering (BIDFC) In this framework, embedding distance between samples should be moderate because of the high similarity between samples in the SAR images. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) database indicate a 91.25% classification accuracy of our method fine-tuned on only 3.13% training data.
  arXiv  Detail & Related papers  (2024-08-07T08:39:33Z)
• Better (pseudo-)labels for semi-supervised instance segmentation [21.703173564795353]
  We introduce a dual-strategy to enhance the teacher model's training process, substantially improving the performance on few-shot learning. We observe marked improvements over a state-of-the-art supervised baseline performance on the LVIS dataset, with an increase of 2.8% in average precision (AP) and 10.3% gain in AP for rare classes.
  arXiv  Detail & Related papers  (2024-03-18T11:23:02Z)
• Unsupervised Domain Adaptation for Semantic Segmentation with Pseudo Label Self-Refinement [9.69089112870202]
  We propose an auxiliary pseudo-label refinement network (PRN) for online refining of the pseudo labels and also localizing the pixels whose predicted labels are likely to be noisy. We evaluate our approach on benchmark datasets with three different domain shifts, and our approach consistently performs significantly better than the previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-10-25T20:31:07Z)
• All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation [67.30502812804271]
  Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning. We propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions.
  arXiv  Detail & Related papers  (2023-05-25T08:19:31Z)
• Boosting Facial Expression Recognition by A Semi-Supervised Progressive Teacher [54.50747989860957]
  We propose a semi-supervised learning algorithm named Progressive Teacher (PT) to utilize reliable FER datasets as well as large-scale unlabeled expression images for effective training. Experiments on widely-used databases RAF-DB and FERPlus validate the effectiveness of our method, which achieves state-of-the-art performance with accuracy of 89.57% on RAF-DB.
  arXiv  Detail & Related papers  (2022-05-28T07:47:53Z)
• Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation [54.49894381464853]
  We propose to leverage both labeled and unlabeled data for instance segmentation with improved accuracy by knowledge distillation. We propose a novel Mask-guided Mean Teacher framework with Perturbation-sensitive Sample Mining. Experiments show that the proposed method improves the performance significantly compared with the supervised method learned from labeled data only.
  arXiv  Detail & Related papers  (2020-07-21T13:27:09Z)
• Uncertainty-aware Self-training for Text Classification with Few Labels [54.13279574908808]
  We study self-training as one of the earliest semi-supervised learning approaches to reduce the annotation bottleneck. We propose an approach to improve self-training by incorporating uncertainty estimates of the underlying neural network. We show our methods leveraging only 20-30 labeled samples per class for each task for training and for validation can perform within 3% of fully supervised pre-trained language models.
  arXiv  Detail & Related papers  (2020-06-27T08:13:58Z)
• Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
  We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training. We experimentally verify that the new dataset can significantly improve the ability of the learned FER model. To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
  arXiv  Detail & Related papers  (2020-05-18T09:36:51Z)
• Improving Semantic Segmentation via Self-Training [75.07114899941095]
  We show that we can obtain state-of-the-art results using a semi-supervised approach, specifically a self-training paradigm. We first train a teacher model on labeled data, and then generate pseudo labels on a large set of unlabeled data. Our robust training framework can digest human-annotated and pseudo labels jointly and achieve top performances on Cityscapes, CamVid and KITTI datasets.
  arXiv  Detail & Related papers  (2020-04-30T17:09:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.