SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial Images

• URL: http://arxiv.org/abs/2108.06810v1
• Date: Sun, 15 Aug 2021 20:38:02 GMT
• Title: SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial Images
• Authors: Tianze Yu, Jianzhe Lin, Lichao Mou, Yuansheng Hua, Xiaoxiang Zhu and Z. Jane Wang
• Abstract summary: Most publicly available datasets for image classification are with single labels, while images are inherently multi-labeled in our daily life. We propose a novel integrated domain adaptation (SCIDA) method for automatic multi-label learning. SCIDA is weakly supervised, i.e., automatically learning the multi-label image classification model from using massive, publicly available single-label images.
• Score: 30.12949142271464
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most publicly available datasets for image classification are with single labels, while images are inherently multi-labeled in our daily life. Such an annotation gap makes many pre-trained single-label classification models fail in practical scenarios. This annotation issue is more concerned for aerial images: Aerial data collected from sensors naturally cover a relatively large land area with multiple labels, while annotated aerial datasets, which are publicly available (e.g., UCM, AID), are single-labeled. As manually annotating multi-label aerial images would be time/labor-consuming, we propose a novel self-correction integrated domain adaptation (SCIDA) method for automatic multi-label learning. SCIDA is weakly supervised, i.e., automatically learning the multi-label image classification model from using massive, publicly available single-label images. To achieve this goal, we propose a novel Label-Wise self-Correction (LWC) module to better explore underlying label correlations. This module also makes the unsupervised domain adaptation (UDA) from single- to multi-label data possible. For model training, the proposed model only uses single-label information yet requires no prior knowledge of multi-labeled data; and it predicts labels for multi-label aerial images. In our experiments, trained with single-labeled MAI-AID-s and MAI-UCM-s datasets, the proposed model is tested directly on our collected Multi-scene Aerial Image (MAI) dataset.

Related papers

• INSITE: labelling medical images using submodular functions and semi-supervised data programming [19.88996560236578]
  Large amounts of labeled data to train deep models creates an implementation bottleneck in resource-constrained settings. We apply informed subset selection to identify a small number of most representative or diverse images from a huge pool of unlabelled data. The newly annotated images are then used as exemplars to develop several data programming-driven labeling functions.
  arXiv  Detail & Related papers  (2024-02-11T12:02:00Z)
• Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning [11.489541220229798]
  In general multi-label learning, a model learns to predict multiple labels or categories for a single input image. This is in contrast with standard multi-class image classification, where the task is predicting a single label from many possible labels for an image.
  arXiv  Detail & Related papers  (2023-10-24T16:36:51Z)
• Pseudo Labels for Single Positive Multi-Label Learning [0.0]
  Single positive multi-label (SPML) learning is a cost-effective solution, where models are trained on a single positive label per image. In this work, we propose a method to turn single positive data into fully-labeled data: Pseudo Multi-Labels.
  arXiv  Detail & Related papers  (2023-06-01T17:21:42Z)
• Multi-Granularity Denoising and Bidirectional Alignment for Weakly Supervised Semantic Segmentation [75.32213865436442]
  We propose an end-to-end multi-granularity denoising and bidirectional alignment (MDBA) model to alleviate the noisy label and multi-class generalization issues. The MDBA model can reach the mIoU of 69.5% and 70.2% on validation and test sets for the PASCAL VOC 2012 dataset.
  arXiv  Detail & Related papers  (2023-05-09T03:33:43Z)
• Dual-Perspective Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels [70.36722026729859]
  We propose a dual-perspective semantic-aware representation blending (DSRB) that blends multi-granularity category-specific semantic representation across different images. The proposed DS consistently outperforms current state-of-the-art algorithms on all proportion label settings.
  arXiv  Detail & Related papers  (2022-05-26T00:33:44Z)
• Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels [86.17081952197788]
  We propose to blend category-specific representation across different images to transfer information of known labels to complement unknown labels. Experiments on the MS-COCO, Visual Genome, Pascal VOC 2007 datasets show that the proposed SARB framework obtains superior performance over current leading competitors.
  arXiv  Detail & Related papers  (2022-03-04T07:56:16Z)
• Structured Semantic Transfer for Multi-Label Recognition with Partial Labels [85.6967666661044]
  We propose a structured semantic transfer (SST) framework that enables training multi-label recognition models with partial labels. The framework consists of two complementary transfer modules that explore within-image and cross-image semantic correlations. Experiments on the Microsoft COCO, Visual Genome and Pascal VOC datasets show that the proposed SST framework obtains superior performance over current state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2021-12-21T02:15:01Z)
• Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attention [45.6809084493491]
  Multi-label few-shot image classification (ML-FSIC) is the task of assigning descriptive labels to previously unseen images. In this paper we propose to use word embeddings as a form of prior knowledge about the meaning of the labels. Our model can infer prototypes for unseen labels without the need for fine-tuning any model parameters.
  arXiv  Detail & Related papers  (2021-12-02T07:59:11Z)
• Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning [86.6929930921905]
  This paper studies how much it can help address domain shifts if we further have a few target samples labeled. To explore the full potential of landmarks, we incorporate a prototypical alignment (PA) module which calculates a target prototype for each class from the landmarks. Specifically, we severely perturb the labeled images, making PA non-trivial to achieve and thus promoting model generalizability.
  arXiv  Detail & Related papers  (2021-04-19T08:46:08Z)
• Instance-Aware Graph Convolutional Network for Multi-Label Classification [55.131166957803345]
  Graph convolutional neural network (GCN) has effectively boosted the multi-label image recognition task. We propose an instance-aware graph convolutional neural network (IA-GCN) framework for multi-label classification.
  arXiv  Detail & Related papers  (2020-08-19T12:49:28Z)

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.