Pith. sign in

REVIEW

Multi-Scale Grouped Prototypes for Interpretable 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 2409.09497 v2 pith:5XQNTUZU submitted 2024-09-14 cs.CV cs.AI

Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentation

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

Prototypical part learning is emerging as a promising approach for making semantic segmentation interpretable. The model selects real patches seen during training as prototypes and constructs the dense prediction map based on the similarity between parts of the test image and the prototypes. This improves interpretability since the user can inspect the link between the predicted output and the patterns learned by the model in terms of prototypical information. In this paper, we propose a method for interpretable semantic segmentation that leverages multi-scale image representation for prototypical part learning. First, we introduce a prototype layer that explicitly learns diverse prototypical parts at several scales, leading to multi-scale representations in the prototype activation output. Then, we propose a sparse grouping mechanism that produces multi-scale sparse groups of these scale-specific prototypical parts. This provides a deeper understanding of the interactions between multi-scale object representations while enhancing the interpretability of the segmentation model. The experiments conducted on Pascal VOC, Cityscapes, and ADE20K demonstrate that the proposed method increases model sparsity, improves interpretability over existing prototype-based methods, and narrows the performance gap with the non-interpretable counterpart models. Code is available at github.com/eceo-epfl/ScaleProtoSeg.

discussion (0)

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