Coarse-To-Fine Incremental Few-Shot Learning

Xiang, Xiang; Tan, Yuwen; Wan, Qian; Ma, Jing; Yuille, Alan; Hager, Gregory D.

doi:10.1007/978-3-031-19821-2_12

Cited by 10 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1, where some pixels are relevant both for deforestation and roadwork). Ni et al [31] explore the coarse-to-fine fewshot setting under the name cross-granularity few-shot with a medical application in mind, Xiang et al [32] develop an incremental variant and, concurrently to the present work, Gong et al [33] investigate taxonomy adaptive cross-domain semantic segmentation (e.g., also incorporating subclasses of known classes) also with only a few labeled shots. To the best of our knowledge however, this is the first work exploring similar ideas specifically adapted to the context of change detection.…”

Section: B Specialization and Subcategorization In Computer Visionmentioning

confidence: 99%

Filtering Specialized Change in a Few-Shot Setting

Hermann

Saha

Zhu

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The aim of change detection in remote sensing usually is not to find all differences between the observations, but rather only specific types of change, such as urban development, deforestation, or even more specialized categories like roadwork. However, often there are no large public datasets available for very fine-grained tasks, and to collect the amount of training data needed for most supervised learning methods is very costly and often prohibitive. For this reason, we formulate the problem of few-shot filtering, where we are provided with a relatively large change detection dataset and, at test time, a few instances of one particular change type that we try to "filter out" of the learned changes. For example, we might train on data of general urban change, and, given some samples of building construction, aim to only predict instances of these on the test set, all without any explicit labels for buildings in the training data. We further investigate a fine-tuning approach to this problem and assess its performance on a public dataset that we adapt to be used in this novel setting. Code will be available at https://gitlab.lrz.de/ai4eo/cd/-/blob/main/fewShotFilteringCd.

show abstract

Section: B Specialization and Subcategorization In Computer Visionmentioning

confidence: 99%