Semi-Supervised Learning via Generalized Maximum Entropy

31 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition (2015, neutral): “This contrasts with common approaches that focus sampling in uncertain regions [28, 1, 35, 14].”
A Minimax Approach to Supervised Learning (2016, methodology): “To that end, we use a similar technique as in the Fenchel’s duality theorem, also used at [11, 12, 13] to address divergence minimization problems.”
A Semantic Loss Function for Deep Learning with Symbolic Knowledge (2017, background): “…of semantic loss to increase the conﬁdence of predictions on unlabeled data is in common with information-theoretic approaches to semi-supervised learning (Grandvalet & Bengio, 2005; Erkan & Altun, 2010), and approaches that increase robustness to output perturbation (Miyato et al., 2016).”
Semi-Supervised Domain Adaptation via Minimax Entropy (2019, methodology): “mble [16], and adversarial approaches [21] have boosted performance in semi-supervised learning, but do not address domain shift. Conditional entropy minimization (CEM) is a widely used method in SSL [12,9]. However, we found that CEM fails to improve performance when there is a large domain gap bet”