Deep Learning on Point Sets for 3 D Classification and Segmentation

How researchers see this paper

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

Set2Graph: Learning Graphs From Sets (2020, methodology): “…paradigm for designing deep models was used for many different tasks, data modalities and transformations, e.g., set learning (Zaheer et al., 2017; Qi et al., 2017), graph learning (Kipf & Welling, 2016; Gilmer et al., 2017; Veliˇckovi´c et al., 2017; Xu et al., 2019; Kondor et al., 2018; Maron…”
Attention-based Deep Multiple Instance Learning (2018, positive): “The attention-based MIL operator was used very recently in (Qi et al., 2017), however, the attention was calculated using the dot product and it performed worse than the max operator.”
Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline (2021, methodology): “3.3 in (Qi et al., 2017b)).”
FSPool: Learning Set Representations with Featurewise Sort Pooling (2019, methodology): “This has been studied in many works such as Deep Sets (Zaheer et al., 2017) and PointNet (Qi et al., 2017), with universal approximation theorems being proven.”
On Learning Sets of Symmetric Elements (2020, methodology): “Indeed, models that respect set symmetries, e.g. (Zaheer et al., 2017; Qi et al., 2017), have become the leading approach for solving such tasks.”