Transductive Semi-Supervised Deep Learning Using Min-Max Features

By Weiwei Shi, Yihong Gong, Chris H. Q. Ding, Zhiheng Ma, Xiaoyu Tao, Nanning Zheng. 2018

240 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Self-Training With Noisy Student Improves ImageNet Classification (2019, methodology): “Works based on pseudo label [44, 37, 68, 1] are similar to self-training, but also suffer the same problem with consistency training, since they rely on a model being trained instead of a converged model with high accuracy to generate pseudo labels.”
Hierarchical Multi-Scale Attention for Semantic Segmentation (2020, background): “[2], other semi-supervised self-training in semantic segmentation [30, 31, 32, 33, 34], and other approaches based on pseudo label such as [4, 35, 36, 3].”
Generating Accurate Pseudo-Labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations (2019, background): “These Pseudolabel (PL) based SSL methods serve as a way to execute transductive learning [14, 26], where label inference on the given test dataset is more important for the user as compared to using the trained model later, on other unseen samples from other data sources.”
Label Propagation for Deep Semi-Supervised Learning (2019, methodology): “[24, 36], assign pseudo-labels to the unlabeled examples.”
An Overview of Deep Semi-Supervised Learning (2020, methodology): “[141] propose to adapt Transductive SSL [77, 78, 181, 160] by treating the labels of unlabeled examples as variables and trying to determine their optimal labels together with the optimal model parameters, by minimizing the proposed loss function through the iterative training process.”
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning (2019, methodology): “Consistency regularization and pseudo-labeling approaches apply different strategies such as a warm-up phase using labeled data [17, 18], uncertainty weighting [11, 19], adversarial attacks [20, 21], or graphconsistency [17, 22].”
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning (2021, methodology): “For a fair comparison, we compare against methods which report results using the CNN-13 architecture: DeepLP (Iscen et al., 2019), TSSDL (Shi et al., 2018), MT (Tarvainen & Valpola, 2017), MT + DeepLP, ICT (Verma et al., 2019), DualStu-dent (Ke et al., 2019), and MixMatch (Berthelot et al., 2019).”
Self-Training: A Survey (2022, unknown): “[Shi et al., 2018] extended this idea to the multiclass classification case with Neural Networks.”
Class-Incremental Learning with Topological Schemas of Memory Spaces (2021, methodology): “It shows that RFL is not suitable for incremental learning.”
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning (2020, methodology): “While pseudo labeling has been proposed before (Lee 2013; Shi et al. 2018; Iscen et al. 2019; Arazo et al. 2019), we revise it by using a self-paced curriculum that we refer to as curriculum labeling, and restarting the model parameters before every iteration in the pseudo-labeling process.”
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation (2020, methodology): “In particular, our model is trained with some human-annotated images and abundant pseudolabeled [42,72,34,3] video sequences.”
Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach (2019, methodology): “Motivated by the nearest neighbor aware semi-supervised framework [Shi et al. , 2018], we artiﬁcially generate pseudo-labels for respective unpaired datasets.”
Debiased Pseudo Labeling in Self-Training (2022, background): “, 2021), assign pseudo labels with the density of local neighborhood (Shi et al., 2018; Iscen et al., 2019), meta-learning (Pham et al.”