paper-with-me

Papers

Understanding Unimodal Bias in Multimodal Deep Linear Networks

2023-12-01 · Yedi Zhang, Peter E. Latham, Andrew Saxe

Using multiple input streams simultaneously to train multimodal neural networks is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where a network overly relies on one modality and ignores others during joint training. We develop a theory of unimodal bias with multimodal deep linear networks to understand how architecture and data statistics influence this bias. This is the first work to calculate the duration of the unimodal phase in learning as a function of the depth at which modalities are fused within the network, dataset statistics, and initialization. We show that the deeper the layer at which fusion occurs, the longer the unimodal phase. A long unimodal phase can lead to a generalization deficit and permanent unimodal bias in the overparametrized regime. Our results, derived for multimodal linear networks, extend to nonlinear networks in certain settings. Taken together, this work illuminates pathologies of multimodal learning under joint training, showing that late and intermediate fusion architectures can give rise to long unimodal phases and permanent unimodal bias. Our code is available at: https://yedizhang.github.io/unimodal-bias.html.

📄 PDF Abstract BibTeX arXiv:2312.00935

Code (1)

yedizhang/unimodal-bias 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective

2024-03-27 · Meiqi Chen, Yixin Cao, Yan Zhang, Chaochao Lu

Recent advancements in Large Language Models (LLMs) have facilitated the development of Multimodal LLMs (MLLMs). Despite their impressive capabilities, MLLMs often suffer from over-reliance on unimodal biases (e.g., lang…

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

VERITE: A Robust Benchmark for Multimodal Misinformation Detection Accounting for Unimodal Bias

2023-04-27 · Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos, Panagiotis C. Petrantonakis

Multimedia content has become ubiquitous on social media platforms, leading to the rise of multimodal misinformation (MM) and the urgent need for effective strategies to detect and prevent its spread. In recent years, th…

Misinformation

Multimodal Sentiment Analysis Based on Causal Reasoning

2024-12-10 · Fuhai Chen, Pengpeng Huang, Xuri Ge, Jie Huang 외

With the rapid development of multimedia, the shift from unimodal textual sentiment analysis to multimodal image-text sentiment analysis has obtained academic and industrial attention in recent years. However, multimodal…

Causal InferencecounterfactualCounterfactual InferenceMultimodal Sentiment Analysis+2

Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation

2024-11-26 · Xu Zheng, Haiwei Xue, Jialei Chen, Yibo Yan 외

Simultaneously using multimodal inputs from multiple sensors to train segmentors is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where multimodal segmentors over rely on certain…

Shifting the Baseline: Single Modality Performance on Visual Navigation & QA

2018-11-01 · Jesse Thomason, Daniel Gordon, Yonatan Bisk

We demonstrate the surprising strength of unimodal baselines in multimodal domains, and make concrete recommendations for best practices in future research. Where existing work often compares against random or majority c…

Question AnsweringVisual Navigation