Minimax Active Learning
원문 초록
Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator. Current active learning techniques either rely on model uncertainty to select the most uncertain samples or use clustering or reconstruction to choose the most diverse set of unlabeled examples. While uncertainty-based strategies are susceptible to outliers, solely relying on sample diversity does not capture the information available on the main task. In this work, we develop a semi-supervised minimax entropy-based active learning algorithm that leverages both uncertainty and diversity in an adversarial manner. Our model consists of an entropy minimizing feature encoding network followed by an entropy maximizing classification layer. This minimax formulation reduces the distribution gap between the labeled/unlabeled data, while a discriminator is simultaneously trained to distinguish the labeled/unlabeled data. The highest entropy samples from the classifier that the discriminator predicts as unlabeled are selected for labeling. We evaluate our method on various image classification and semantic segmentation benchmark datasets and show superior performance over the state-of-the-art methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual Tasks
Clustering-Guided Class Activation for Weakly Supervised Semantic Segmentation
DEU-Net: Dual-Encoder U-Net for Automated Skin Lesion Segmentation
A Robust Feature Downsampling Module for Remote Sensing Visual Tasks
Learning Better Registration to Learn Better Few-Shot Medical Image Segmentation: Authenticity, Diversity, and Robustness
Cross-Domain Few-Shot Semantic Segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.