Pith. sign in

REVIEW

Compositional Prototypical Networks for Few-Shot Classification

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 2306.06584 v1 pith:WI2UJXVV submitted 2023-06-11 cs.CV

Compositional Prototypical Networks for Few-Shot Classification

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

It is assumed that pre-training provides the feature extractor with strong class transferability and that high novel class generalization can be achieved by simply reusing the transferable feature extractor. In this work, our motivation is to explicitly learn some fine-grained and transferable meta-knowledge so that feature reusability can be further improved. Concretely, inspired by the fact that humans can use learned concepts or components to help them recognize novel classes, we propose Compositional Prototypical Networks (CPN) to learn a transferable prototype for each human-annotated attribute, which we call a component prototype. We empirically demonstrate that the learned component prototypes have good class transferability and can be reused to construct compositional prototypes for novel classes. Then a learnable weight generator is utilized to adaptively fuse the compositional and visual prototypes. Extensive experiments demonstrate that our method can achieve state-of-the-art results on different datasets and settings. The performance gains are especially remarkable in the 5-way 1-shot setting. The code is available at https://github.com/fikry102/CPN.

discussion (0)

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