Pith. sign in

REVIEW 3 cited by

Learning Modality Knowledge Alignment for Cross-Modality Transfer

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 2406.18864 v1 pith:HV2ID3Y2 submitted 2024-06-27 cs.CV

classification cs.CV
keywords modalitytransferknowledgecross-modalityalignmentdataexistingexperiments
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Cross-modality transfer aims to leverage large pretrained models to complete tasks that may not belong to the modality of pretraining data. Existing works achieve certain success in extending classical finetuning to cross-modal scenarios, yet we still lack understanding about the influence of modality gap on the transfer. In this work, a series of experiments focusing on the source representation quality during transfer are conducted, revealing the connection between larger modality gap and lesser knowledge reuse which means ineffective transfer. We then formalize the gap as the knowledge misalignment between modalities using conditional distribution P(Y|X). Towards this problem, we present Modality kNowledge Alignment (MoNA), a meta-learning approach that learns target data transformation to reduce the modality knowledge discrepancy ahead of the transfer. Experiments show that out method enables better reuse of source modality knowledge in cross-modality transfer, which leads to improvements upon existing finetuning methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. ProtoHGF-Net: Prototype HyperGraph Fusion with Intra-modal Calibration for RGBT Object Detection

    cs.CV 2026-08 conditional novelty 6.0 of 10

    ProtoHGF-Net fuses RGB and thermal features via prototype-level hypergraph propagation with teacher-mask calibration, reporting 85.9%, 88.2%, and 79.1% mAP50 on DroneVehicle, DVTOD, and FLIR.

  2. Improving Factuality of 3D Brain MRI Report Generation with Paired Image-domain Retrieval and Text-domain Augmentation

    cs.CV 2024-11 conditional novelty 6.0 of 10

    PIRTA generates acute ischemic stroke radiology reports by retrieving similar 3D DWI/ADC images and augmenting LLM generation with their paired expert reports, improving ischemic-territory accuracy over direct image-t...

  3. D-CAT: Decoupled Cross-Attention Transfer between Sensor Modalities for Unimodal Inference

    cs.LG 2025-09 reject novelty 4.0 of 10

    D-CAT aligns the K^T V attention products of a source and target sensor model during training, claiming unimodal inference gains of up to 7-10% F1 on HAR datasets, with mixed empirical support.

Pith tools