Pith. sign in

REVIEW

SALA: Soft Assignment Local Aggregation for Parameter Efficient 3D Semantic Segmentation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2012.14929 v2 pith:LJZTXMFX submitted 2020-12-29 cs.CV

SALA: Soft Assignment Local Aggregation for Parameter Efficient 3D Semantic Segmentation

classification cs.CV
keywords assignmentaggregationefficientlocalnetworkparameterfunctionlearn
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In this work, we focus on designing a point local aggregation function that yields parameter efficient networks for 3D point cloud semantic segmentation. We explore the idea of using learnable neighbor-to-grid soft assignment in grid-based aggregation functions. Previous methods in literature operate on a predefined geometric grid such as local volume partitions or irregular kernel points. A more general alternative is to allow the network to learn an assignment function that best suits the end task. Since it is learnable, this mapping is allowed to be different per layer instead of being applied uniformly throughout the depth of the network. By endowing the network with the flexibility to learn its own neighbor-to-grid assignment, we arrive at parameter efficient models that achieve state-of-the-art (SOTA) performance on S3DIS with at least 10$\times$ less parameters than the current reigning method. We also demonstrate competitive performance on ScanNet and PartNet compared with much larger SOTA models.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.