1 citations · 1 across the 10 of their papers we have counts for
7 papers · 1 filter
OccAnyScene: Towards Unified Indoor-Outdoor 3D Occupancy Prediction
Junjie Liu, Wanshui Gan, Zitong Dai +6
3D occupancy prediction is fundamental to scene understanding, yet existing 3D semantic occupancy methods are typically specialized to fixed scene types and occupancy protocols. We…
Efficient Adversarial Training via Criticality-Aware Fine-Tuning
Wenyun Li, Zheng Zhang, Dongmei Jiang +2
Vision Transformer (ViT) models have achieved remarkable performance across various vision tasks, with scalability being a key advantage when applied to large datasets. This scalab…
DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection
Guiping Cao, Xiangyuan Lan, Wenjian Huang +3
Popular transformer detectors have achieved promising performance through query-based learning using attention mechanisms. However, the roles of existing decoder query types (e.g.,…
Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection
Guiping Cao, Wenjian Huang, Xiangyuan Lan +3
Small Object Detection (SOD) poses significant challenges due to limited information and the model's low class prediction score. While Transformer-based detectors have shown promis…
Open-Det: An Efficient Learning Framework for Open-Ended Detection
Guiping Cao, Tao Wang, Wenjian Huang +3
Open-Ended object Detection (OED) is a novel and challenging task that detects objects and generates their category names in a free-form manner, without requiring additional vocabu…
Transferable Adversarial Face Attack with Text Controlled Attribute
Wenyun Li, Zheng Zhang, Xiangyuan Lan +1
Traditional adversarial attacks typically produce adversarial examples under norm-constrained conditions, whereas unrestricted adversarial examples are free-form with semantically…
AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal Alignment
Yan Li, Yifei Xing, Xiangyuan Lan +3
Cross-modal alignment is crucial for multimodal representation fusion due to the inherent heterogeneity between modalities. While Transformer-based methods have shown promising res…