Pith. sign in

REVIEW 2 cited by

What Makes Training Multi-Modal Classification Networks Hard?

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 1905.12681 v5 pith:GPHXZZDE submitted 2019-05-29 cs.CV cs.LG

classification cs.CVcs.LG
keywords multi-modaldifferentmodalitiesnetworkoverfittingsingle-modaltrainingaction
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Consider end-to-end training of a multi-modal vs. a single-modal network on a task with multiple input modalities: the multi-modal network receives more information, so it should match or outperform its single-modal counterpart. In our experiments, however, we observe the opposite: the best single-modal network always outperforms the multi-modal network. This observation is consistent across different combinations of modalities and on different tasks and benchmarks. This paper identifies two main causes for this performance drop: first, multi-modal networks are often prone to overfitting due to increased capacity. Second, different modalities overfit and generalize at different rates, so training them jointly with a single optimization strategy is sub-optimal. We address these two problems with a technique we call Gradient Blending, which computes an optimal blend of modalities based on their overfitting behavior. We demonstrate that Gradient Blending outperforms widely-used baselines for avoiding overfitting and achieves state-of-the-art accuracy on various tasks including human action recognition, ego-centric action recognition, and acoustic event detection.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 28 citations worldwide. Full citation record

  1. MC2SleepNet: Multi-modal Cross-masking with Contrastive Learning for Sleep Stage Classification

    eess.SP 2025-02 conditional novelty 6.0 of 10

    MC2SleepNet fuses raw EEG and spectrogram views with contrastive learning and cross-masking to reach state-of-the-art sleep staging accuracy on two public datasets.

  2. Foundation Models for Astrophysics

    astro-ph.IM 2026-08 conditional novelty 3.0 of 10

    Astronomical 'foundation models' largely reuse transformers and self-supervised pretraining, but evidence of transfer to new instruments, populations, or tasks remains rare; the paper argues such evidence, not archite...

Pith tools