issues
search
JisuHann
/
One-day-One-paper
Review paper
3
stars
0
forks
source link
Set: Set-to-Vector, Vector-to-set
#37
Closed
JisuHann
closed
2 years ago
JisuHann
commented
2 years ago
Set-to-Vector
Deep Sets(NIPS2017)
Learning Functions over Sets via Permutation Adversarial Networks(ACCV2020)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks(ICML2019)
Vector-to-Set
DSPN: Deep Set Prediction Networks (NIPS2019)
TSPN: Conditional Set Generation with Transformers (ICMLW2020)
JisuHann
commented
2 years ago
Deep Sets(NIPS2017)
paper
Idea
Objective functions defined on sets that are invariant to permutations
Function acting on sets must be
permutation invariant
to the order of objects in the set
Deep Sets
JisuHann
commented
2 years ago
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks(ICML2019)
paper
Idea
Set structured data - permutation invariant set of solution
set-input problem
Critical requirements
permutation invariant: the output of the model should not change under any permutation of the elements in the input set
able to process input set of any size
Application (set-input problem)
multiple instance learning: (set of instances) -> (label for the entire set)
3D shape recognition, sequence ordering
various set operations
Model
Encoder-decoder architecture that rely on attention mechanism
Attention scheme inspired by inducing point methods from sparse Gaussian process literature
self-attention
every element in an input set -> naturally encode pairwise- or higher-order interactions btw elements in the set
aggregate feature: each cluster center X heavily depends its location relative to the other clusters
Encoder
Decoder
tasks
Maximum Value Regression
Counting Unique Characters
Amortized Clustering with Mixture of Gaussinas
Set anomaly detection
Point cloud classification
JisuHann
commented
2 years ago
Learning Functions over Sets via Permutation Adversarial Networks(ACCV2020)
Set-to-Vector
Vector-to-Set