REVIEW 5 cited by
Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization
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
read the original abstract
Fusing and balancing multi-modal inputs from novel sensors for dense prediction tasks, particularly semantic segmentation, is critically important yet remains a significant challenge. One major limitation is the tendency of multi-modal frameworks to over-rely on easily learnable modalities, a phenomenon referred to as unimodal dominance or bias. This issue becomes especially problematic in real-world scenarios where the dominant modality may be unavailable, resulting in severe performance degradation. To this end, we apply a simple but effective plug-and-play regularization term based on functional entropy, which introduces no additional parameters or modules. This term is designed to intuitively balance the contribution of each visual modality to the segmentation results. Specifically, we leverage the log-Sobolev inequality to bound functional entropy using functional-Fisher-information. By maximizing the information contributed by each visual modality, our approach mitigates unimodal dominance and establishes a more balanced and robust segmentation framework. A multi-scale regularization module is proposed to apply our proposed plug-and-play term on high-level features and also segmentation predictions for more balanced multi-modal learning. Extensive experiments on three datasets demonstrate that our proposed method achieves superior performance, i.e., +13.94%, +3.25%, and +3.64%, without introducing any additional parameters.
Forward citations
Cited by 5 Pith papers
-
BiXFormer: A Robust Framework for Maximizing Modality Effectiveness in Multi-Modal Semantic Segmentation
A multi-modal semantic segmentation framework that processes RGB and non-RGB sensors separately, matches labels in two stages, and aligns cross-modal queries with a VAE refiner.
-
Partial CLIP is Enough: Chimera-Seg for Zero-shot Semantic Segmentation
A partial, frozen CLIP block mounted on a segmentation backbone, plus selective distillation to CLIP's CLS token, improves zero-shot semantic segmentation by about 1 hIoU point on two datasets.
-
Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation
AnySeg trains a segmentor to handle arbitrary combinations of visual modalities through unimodal and cross-modal distillation, improving mean mIoU by +6.37% on MUSES and +6.15% on DELIVER over prior state-of-the-art.
-
MLLMs are Deeply Affected by Modality Bias
A position paper with a case study showing that multimodal LLMs rely on language priors and underuse visual input, together with a research roadmap and calls for balanced training.
-
EGFormer: Towards Efficient and Generalizable Multimodal Semantic Segmentation
EGFormer dynamically scores and drops the least useful sensor modality at each processing stage, cutting parameters by up to 91 percent and GFLOPs by half while keeping segmentation accuracy competitive.
Discussion (0). Continue with ORCID to comment.