AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception

Hassan Akbari, Dan Kondratyuk, Yin Cui, Rachel Hornung, Huisheng Wang, Hartwig Adam

NeurIPS 2023 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
alternate NCE and softmax objectives instead of summing them (ablation)IMP on I21K · ImageNet1K linear probeaccuracy: 47.6 -> 49.9Improved
alternate NCE and softmax objectives instead of summing them (ablation)IMP on I21K · CIFAR-100 linear probeaccuracy: 82.4 -> 84.1Improved
add softmax objective alternating with NCE (ablation)IMP on I21K · ImageNet1K linear probeaccuracy: 39.8 -> 49.9Improved
sum NCE and softmax objectives instead of NCE only (ablation)IMP on I21K · CIFAR-100 linear probeaccuracy: 84.0 -> 82.4Hurt
replace dense with 4-expert experts-choose MoE (ablation)IMP-B · ImageNet zero-shotaccuracy: 59.8 -> 68.1Improved
experts-choose routing instead of tokens-choose (ablation)IMP-B single tower MoE · ImageNet zero-shotaccuracy: 62.5 -> 68.1Improved
two towers instead of one tower with experts-choose (ablation)IMP-B MoE · ImageNet zero-shotaccuracy: 68.1 -> 68.4No clear effect
train-time IMP prompts instead of no prompt (ablation)IMP · ImageNet zero-shotaccuracy: 51.4 -> 56.5Improved
train-time IMP prompts instead of no prompt (ablation)IMP · CIFAR-100 zero-shotaccuracy: 67.5 -> 60.5Hurt
add I21K with NCE+Softmax to CC pretraining (ablation)IMP-S · ImageNet linearaccuracy: 15.2 -> 49.0Improved
add softmax to NCE on CC + I21K (ablation)IMP-S · ImageNet zero-shotaccuracy: 39.1 -> 49.4Improved
add LAION to CC + I21K (NCE+Softmax) (ablation)IMP-S · Flickr30k T->Irecall: 38.6 -> 51.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy