Deep Streaming Label Learning

By Zhen Wang, Liu Liu, Dacheng Tao. 2020

42 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

Balancing Stability and Plasticity through Advanced Null Space in Continual Learning (2022, neutral): “Regularization-based methods can be divided into two classes: one is to distill knowledge from the previous model which is trained on the previous tasks [14, 15, 23, 36, 52, 59]; another is to explicitly use a regularizer to penalize the update of important parameters of previous tasks, preventing t”
Online Continual Learning with Contrastive Vision Transformer (2022, background): “DER++ [9] combines rehearsal with distillation loss [36,83,47] to retrain past experience and obtain state-of-the-art performance.”
Continual Learning through Retrieval and Imagination (2022, background): “Unfortunately, most of the exiting methods fail to satisfy all these guidelines mentioned above (Chaudhry et al. 2021; Wang et al. 2020; Lopez-Paz et al. 2017; Wei et al. 2021; Riemer et al. 2019; Kong et al. 2021; Schwarz et al. 2018; Zhu et al. 2020).”
Learning to Classify With Incremental New Class (2021, unknown): “Wang et al. [36] studied novelty detection under multilabel settings and proposed deep streaming label learning (DSLL) to effectively classify instances with newly emerged labels.”
The Emerging Trends of Multi-Label Learning (2020, methodology): “In addition, [35] further theoretically proves”
Adaptive Curriculum Learning (2021, background): “KL divergence is frequently used to maintain useful knowledge learned from a pre-trained model [4, 5, 17, 43].”
Multi-label Few-shot Learning with Semantic Inference (Student Abstract) (2021, methodology): “The results consistently show that the proposed model DESIRE-Net outperforms the baselines on the AUC metric for both 1-shot and 5-shot, 5-way and 10-way.”
A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning (2022, methodology): “During the training procedure, the trajectory segments are randomly sampled from the same trajectory to break the temporal correlations of the training data, which was also adopted by (Seo et al., 2020; Wang et al., 2020b; 2019).”
SIN: Semantic Inference Network for Few-Shot Streaming Label Learning (2022, methodology): “As new labels usually emerge from open and dynamic environments [1]–[3], [7], [21], streaming label learning is proposed to facilitate the learning system with the capability of modeling new labels effectively [8], [9].”
Probabilistic Label Tree for Streaming Multi-Label Learning (2021, methodology): “Recently, DSLL [25] proposes a novel DNN-based framework to effectively model the emerging new labels.”
IExpressNet: Facial Expression Recognition with Incremental Classes (2020, background): “We would like to follow the recent successful works [65] in multi-label learning and generalize IExpressNet to multi-label setup in the future work.”
CIFDM: Continual and Interactive Feature Distillation for Multi-Label Stream Learning (2021, background): “Deep Stream Label Learning (DSLL) [20] takes advantages from the previous labels and models to train a new model for novel classes.”
Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint (2022, background): “Subsequent works improved the performance in more complicated cases such as discrete-continuous mixtures [11, 41], segmentation [66, 70, 72] and continue learning [61, 62].”
Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression (2021, background): “However, there is little work on the robustness of localization losses to noisy bboxes, even though a number of methods have been proposed for robust learning with noisy labels, anchors, and bboxes [27, 26, 12, 10, 15, 37, 38, 25, 19, 20].”