Learning with Noisy Labels: Interconnection of Two Expectation-Maximizations
원문 초록
Labor-intensive labeling becomes a bottleneck in developing computer vision algorithms based on deep learning. For this reason, dealing with imperfect labels has increasingly gained attention and has become an active field of study. We address learning with noisy labels (LNL) problem, which is formalized as a task of finding a structured manifold in the midst of noisy data. In this framework, we provide a proper objective function and an optimization algorithm based on two expectation-maximization (EM) cycles. The separate networks associated with the two EM cycles collaborate to optimize the objective function, where one model is for distinguishing clean labels from corrupted ones while the other is for refurbishing the corrupted labels. This approach results in a non-collapsing LNL-flywheel model in the end. Experiments show that our algorithm achieves state-of-the-art performance in multiple standard benchmarks with substantial margins under various types of label noise.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sfumato Supervision: Learning Instance Segmentation with Noisy Labels
On the Role of Label Noise in the Feature Learning Process
Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels
Exploring Video-Based Driver Activity Recognition under Noisy Labels
Early Stopping Against Label Noise Without Validation Data
Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space
토론
이 논문과 연결된 포럼 글이 아직 없습니다.