Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities
원문 초록
Image modality is not perfect as it often fails in certain conditions, e.g., night and fast motion. This significantly limits the robustness and versatility of existing multi-modal (i.e., Image+X) semantic segmentation methods when confronting modality absence or failure, as often occurred in real-world applications. Inspired by the open-world learning capability of multi-modal vision-language models (MVLMs), we explore a new direction in learning the modality-agnostic representation via knowledge distillation (KD) from MVLMs. Intuitively, we propose Any2Seg, a novel framework that can achieve robust segmentation from any combination of modalities in any visual conditions. Specifically, we first introduce a novel language-guided semantic correlation distillation (LSCD) module to transfer both inter-modal and intra-modal semantic knowledge in the embedding space from MVLMs, e.g., LanguageBind. This enables us to minimize the modality gap and alleviate semantic ambiguity to combine any modalities in any visual conditions. Then, we introduce a modality-agnostic feature fusion (MFF) module that reweights the multi-modal features based on the inter-modal correlation and selects the fine-grained feature. This way, our Any2Seg finally yields an optimal modality-agnostic representation. Extensive experiments on two benchmarks with four modalities demonstrate that Any2Seg achieves the state-of-the-art under the multi-modal setting (+3.54 mIoU) and excels in the challenging modality-incomplete setting(+19.79 mIoU).
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
KDMOS:Knowledge Distillation for Motion Segmentation
Towards Scalable and Generalizable Earth Observation Data Mining via Foundation Model Composition
Building Lightweight Semantic Segmentation Models for Aerial Images Using Dual Relation Distillation
CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal Images
DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition
Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.