Topic-based label distribution learning to exploit label ambiguity for scene classification
Autor: | Biao He, Jianqiao Luo, Kai Wang, Bailin Li, Yang Ou |
---|---|
Rok vydání: | 2021 |
Předmět: |
Topic model
0209 industrial biotechnology Exploit Computer science business.industry media_common.quotation_subject ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Probabilistic logic Pattern recognition 02 engineering and technology Ambiguity Construct (python library) Image (mathematics) ComputingMethodologies_PATTERNRECOGNITION 020901 industrial engineering & automation Artificial Intelligence 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Feature learning Software Aerial image media_common |
Zdroj: | Neural Computing and Applications. 33:16181-16196 |
ISSN: | 1433-3058 0941-0643 |
Popis: | One of the greatest challenges for scene classification is the lack of sufficient training samples. Label distribution learning (LDL) is proven to be effective in handling insufficient samples by exploiting label ambiguity. However, LDL has never been used in scene classification because the correlations among scene classes are unavailable, making it impossible to construct label distribution vectors for images. In this paper, we aim to transform LDL into scene classification. To this end, we introduce a probabilistic topic model (PTM) to capture label correlations, and propose a method termed as topic-based LDL (TB-LDL). By treating scene classes as documents in the PTM, the discovered topics indicate typical scene patterns, and class-topic distributions provide label measurements on multiple topics. For each topic, scenes with similar label measurements can be considered as neighbouring labels. The label distributions smooth image truth labels based on label correlations, which can formulate the label ambiguity of scene images. Training networks with the label distributions can prevent over-fitting and assist feature learning. Extensive experiments on two challenging datasets, namely the aerial image dataset (AID) and NWPU_RESISC45 (NR), demonstrate that our method is effective, especially when the amount of training data is limited. |
Databáze: | OpenAIRE |
Externí odkaz: | |
Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |