Pith. sign in

REVIEW 4 cited by

Efficient Learning of Domain-invariant Image Representations

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1301.3224 v5 pith:ARN6B7AH submitted 2013-01-15 cs.LG

Judy Hoffman , Erik Rodner , Jeff Donahue , Trevor Darrell , Kate Saenko This is my paper · ORCID
classification cs.LG
keywords domainalgorithmclassifierdatasetsefficientfeaturesimagelearning
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We present an algorithm that learns representations which explicitly compensate for domain mismatch and which can be efficiently realized as linear classifiers. Specifically, we form a linear transformation that maps features from the target (test) domain to the source (training) domain as part of training the classifier. We optimize both the transformation and classifier parameters jointly, and introduce an efficient cost function based on misclassification loss. Our method combines several features previously unavailable in a single algorithm: multi-class adaptation through representation learning, ability to map across heterogeneous feature spaces, and scalability to large datasets. We present experiments on several image datasets that demonstrate improved accuracy and computational advantages compared to previous approaches.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm

    cs.LG 2024-12 conditional novelty 6.0 of 10

    RL-OSHeDA, a two-stage representation learning method with pseudo-labeling, outperforms existing domain adaptation baselines on 56 open-set heterogeneous domain adaptation tasks.

  2. Preempting Text Sanitization Utility in Resource-Constrained Privacy-Preserving LLM Interactions

    cs.CR 2024-11 conditional novelty 6.0 of 10

    A local small language model can predict when a differentially private sanitized prompt will still yield useful LLM output, saving up to 20% of wasted API calls, and an exact-nearest-neighbor implementation of the dX-...

  3. PixelVAE++: Improved PixelVAE with Discrete Prior

    cs.CV 2019-08 conditional novelty 6.0 of 10

    PixelVAE++ replaces Gaussian latents with discrete RBM-prior latents in a PixelCNN++ decoder, achieving small log-likelihood gains on MNIST, Omniglot, and CIFAR-10, but with no code release and weak evidence that the ...

  4. Knowledge distillation for semi-supervised domain adaptation

    cs.LG 2019-08 conditional novelty 4.0 of 10

    Using a teacher network's soft labels on unlabeled target images to train a student network yields improved white matter hyperintensity segmentation over baseline and adversarial adaptation in most but not all cross-s...

Pith tools