Generalized Zero-Shot Learning with Deep Calibration Network

By Shichen Liu, Mingsheng Long, Jianmin Wang, Michael I. Jordan. 2018

265 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.

Citations in the corpus

Dark Experience for General Continual Learning: a Strong, Simple Baseline (2020, background): “This adheres to (Hinton et al. , 2015); indeed, matching logits is a special case of distillation that avoids the information loss occurring in probability space due to the squashing function (e.g. softmax) (Liu et al. , 2018).”
Task-Driven Modular Networks for Zero-Shot Compositional Learning (2019, methodology): “In our work, we adopt the same methodology and calibration technique, although alternative calibration techniques have also been explored in literature [4, 17].”
A Meta-Learning Framework for Generalized Zero-Shot Learning (2019, background): “This setting is popularly known as Zero-Shot Learning (ZSL), and has drawn a considerable interest recently [44, 32, 47, 5, 38, 53, 46, 27, 39, 7, 29, 4, 33, 10, 62, 41, 23].”
Normalization Matters in Zero-Shot Learning (2020, methodology): “[39] Shichen Liu, Mingsheng Long, Jianmin Wang, and Michael I Jordan.”
A Review of Generalized Zero-Shot Learning Methods (2020, methodology): “matic view of the proposed method by Jian et al. [95]. to the unseen classes based on the class similarity score between visual features of the seen and unseen classes. Deep calibration network (DCN) [2] maps both visual features and semantic representations into a common Kdimensional latent space b”
Large-Scale Multi-Label Text Classification on EU Legislation (2019, methodology): “Finally, we plan to investigate Generalized Zero-Shot Learning (Liu et al., 2018).”
Attribute Prototype Network for Zero-Shot Learning (2020, background): “Recent advances in zero-shot learning mainly focus on learning better visual-semantic embeddings [26, 50, 17, 5] or training generative models to synthesize features [44, 45, 57, 56, 19, 33].”
Region Graph Embedding Network for Zero-Shot Learning (2020, methodology): “In this paper, to solve the realistic inductive ZSL and GZSL tasks (unseen images are inaccessible [27, 19]), we propose a Region Graph Embedding Network (RGEN) with the transfer and balance losses as supervision.”