iconLogo
Published:2025/12/3 12:43:16

可視光&赤外線人物識別!モダリティバイアス除去ってスゴくない?✨ 超要約:環境に強い人物検索技術!

🌟 ギャル的キラキラポイント ● 夜でもバッチリ!🌃 赤外線画像で人物特定! ● モダリティバイアス(変なクセみたいなの)を除去!😎 ● デュアルレベルってなんかカッコイイ!✨

🌟 詳細解説 ● 背景 監視カメラとかで、夜とか悪天候でも人を見分けたいってこと、あるじゃん?👀 この研究は、可視光(普通のカメラ)と赤外線(熱を感知する)を組み合わせて、そういうのを実現しようとしてるんだって!

● 方法 「デュアルレベルのモダリティバイアス除去学習 (DMDL)」っていう方法を使うみたい!🤔 つまり、モデル全体と、細かい部分の両方で、変なクセ(モダリティバイアス)を取り除くんだって!

● 結果 色んな環境でも、しっかり人物を特定できるようになったみたい!🎉 従来の技術より、もっと賢くなったってことだね!

続きは「らくらく論文」アプリで

Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identification

Jiaze Li / Yan Lu / Bin Liu / Guojun Yin / Mang Ye

Two-stage learning pipeline has achieved promising results in unsupervised visible-infrared person re-identification (USL-VI-ReID). It first performs single-modality learning and then operates cross-modality learning to tackle the modality discrepancy. Although promising, this pipeline inevitably introduces modality bias: modality-specific cues learned in the single-modality training naturally propagate into the following cross-modality learning, impairing identity discrimination and generalization. To address this issue, we propose a Dual-level Modality Debiasing Learning (DMDL) framework that implements debiasing at both the model and optimization levels. At the model level, we propose a Causality-inspired Adjustment Intervention (CAI) module that replaces likelihood-based modeling with causal modeling, preventing modality-induced spurious patterns from being introduced, leading to a low-biased model. At the optimization level, a Collaborative Bias-free Training (CBT) strategy is introduced to interrupt the propagation of modality bias across data, labels, and features by integrating modality-specific augmentation, label refinement, and feature alignment. Extensive experiments on benchmark datasets demonstrate that DMDL could enable modality-invariant feature learning and a more generalized model.

cs / cs.CV