Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Enhancing multimodal cooperation via sample-level modality valuation

About

One primary topic of multimodal learning is to jointly incorporate heterogeneous information from different modalities. However most models often suffer from unsatisfactory multimodal cooperation which cannot jointly utilize all modalities well. Some methods are proposed to identify and enhance the worse learnt modality but they are often hard to provide the fine-grained observation of multimodal cooperation at sample-level with theoretical support. Hence it is essential to reasonably observe and improve the fine-grained cooperation between modalities especially when facing realistic scenarios where the modality discrepancy could vary across different samples. To this end we introduce a sample-level modality valuation metric to evaluate the contribution of each modality for each sample. Via modality valuation we observe that modality discrepancy indeed could be different at sample-level beyond the global contribution discrepancy at dataset-level. We further analyze this issue and improve cooperation between modalities at sample-level by enhancing the discriminative ability of low-contributing modalities in a targeted manner. Overall our methods reasonably observe the fine-grained uni-modal contribution and achieve considerable improvement. The source code and dataset are available at https://github.com/GeWu-Lab/Valuate-and-Enhance-Multimodal-Cooperation.

Yake Wei, Ruoxuan Feng, Zihe Wang, Di Hu• 2023

Related benchmarks

TaskDatasetResultRank
Action RecognitionUCF-101
Top-1 Acc83.52
225
Multimodal ClassificationCREMA-D
Accuracy78.72
53
Multimodal ClassificationKinetics-Sounds
Accuracy69
25
Multimodal ClassificationNVGesture
Accuracy83.52
23
Action RecognitionKS
Accuracy66.92
15
Multimodal ClassificationVGGSound large-scale (test)
ACC50.31
9
Action RecognitionMM-Debiased
Accuracy84.71
8
Showing 7 of 7 rows

Other info

Code

Follow for update