.png){kind=icon}
Return
Downstream-Pretext Domain Knowledge Traceback for Active Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2024.3391897.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Active learning (AL) is designed to construct a high-quality labeled dataset by iteratively selecting the most informative samples. Such sampling heavily relies on data representation, while recently pre-training is popular for robust feature learning. However, as pre-training utilizes low-level pretext tasks that lack annotation, directly using pre-trained representation in AL is inadequate for determining the sampling score. To address this problem, we propose a downstream-pretext domain knowledge traceback (DOKT) method that traces the data interactions of downstream knowledge and pre-training guidance for selecting diverse and instructive samples near the decision boundary. DOKT consists of a traceback diversity indicator and a domain-based uncertainty estimator. The diversity indicator constructs two feature spaces based on the pre-training pretext model and the downstream knowledge from annotation, by which it locates the neighbors of unlabeled data from the downstream space in the pretext space to explore the interaction of samples. With this mechanism, DOKT unifies the data relations of low-level and high-level representations to estimate traceback diversity. Next, in the uncertainty estimator, domain mixing is designed to enforce perceptual perturbing to unlabeled samples with similar visual patches in the pretext space. Then the divergence of perturbed samples is measured to estimate the domain uncertainty. As a result, DOKT selects the most diverse and important samples based on these two modules. The experiments conducted on ten datasets show that our model outperforms other state-of-the-art methods and generalizes well to various application scenarios such as semantic segmentation and image captioning.
Keywords:
Task analysis
Uncertainty
Annotations
Data models
Training
Visualization
Transformers
Active learning
pretext training
domain knowledge
self-supervised learning
Journal
IF:
9.7
Papers:
4.5K
Citations:
2.4W
Organization
Cited Papers
Weak-Labeled Active Learning With Conditional Label Dependence for Multilabel Image Classification
OAAI
OAAIShareSaveShareSaveShareSaveBACTERIAL INGESTION, TUMOR NECROSIS FACTOR-ALPHA, AND HEAT INDUCE PROGRAMMED CELL DEATH IN ACTIVATED NEUTROPHILS.png)
Shock
ShockIF0
PREAI
ShareSaveShareSave
View more