Entity · paper

Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification

paperactiveprovisionalco-learning-for-missing-arbitrary-modalities-in-multi-modal-classification-5dda1abc·1 events·first seen 2d ago

Aliases: Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification

More like this (12)

Latent World Recovery for Multimodal Learning with Missing Modalities Multimodal Learning multimodal classification models MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities multimodal pretraining Multi-Task Learning Test-Time Training for Modality Order Consistency in Vision-Language Models multimodal embedding Multimodal Large Language Models Multimodal Augmented Generation via Multimodal Retrieval Workshop Scaling Native Multimodal Pre-Training From Scratch Multimodal Gain

Recent events (1)

4arXiv · cs.LG·2d ago·source ↗

Co-learning framework for multi-modal classification with arbitrary missing modalities

A new arXiv preprint introduces a co-learning framework for multi-modal classification that handles arbitrary missing modalities at inference time, without assuming predefined missing patterns. Two complementary methods are proposed — one operating at the feature level and one at the decision level — evaluated on two multi-modal benchmarks. The approach prioritizes inter-modal collaboration over fusion, showing robustness gains across both minimal and extreme missing-modality conditions.

Multimodal Progress Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification