Pith. sign in

REVIEW

Semantically Consistent Regularization for Zero-Shot Recognition

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 1704.03039 v1 pith:SYXAYWCT submitted 2017-04-10 cs.CV cs.AIcs.LG

Semantically Consistent Regularization for Zero-Shot Recognition

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

The role of semantics in zero-shot learning is considered. The effectiveness of previous approaches is analyzed according to the form of supervision provided. While some learn semantics independently, others only supervise the semantic subspace explained by training classes. Thus, the former is able to constrain the whole space but lacks the ability to model semantic correlations. The latter addresses this issue but leaves part of the semantic space unsupervised. This complementarity is exploited in a new convolutional neural network (CNN) framework, which proposes the use of semantics as constraints for recognition.Although a CNN trained for classification has no transfer ability, this can be encouraged by learning an hidden semantic layer together with a semantic code for classification. Two forms of semantic constraints are then introduced. The first is a loss-based regularizer that introduces a generalization constraint on each semantic predictor. The second is a codeword regularizer that favors semantic-to-class mappings consistent with prior semantic knowledge while allowing these to be learned from data. Significant improvements over the state-of-the-art are achieved on several datasets.

discussion (0)

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