20 citations · 25 across the 21 of their papers we have counts for
22 papers
From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentation
Haowen Gu, Gensheng Pei, Junzhu Mao +3
Although Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in Medical Visual Question Answering (Med-VQA), their reliance on global image features o…
MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQA
Haowen Gu, Gensheng Pei, Zeren Sun +4
Medical Visual Question Answering (Med-VQA) holds significant promise for clinical decision support, yet faces challenges due to limited annotated data and the high computational d…
PEARL: Geometry Aligns Semantics for Training-Free Open-Vocabulary Semantic Segmentation
Gensheng Pei, Xiruo Jiang, Xinhao Cai +3
Training-free open-vocabulary semantic segmentation (OVSS) promises rapid adaptation to new label sets without retraining. Yet, many methods rely on heavy post-processing or handle…
Beyond Quadratic: Linear-Time Change Detection with RWKV
Zhenyu Yang, Gensheng Pei, Tao Chen +4
Existing paradigms for remote sensing change detection are caught in a trade-off: CNNs excel at efficiency but lack global context, while Transformers capture long-range dependenci…
Efficiency Follows Global-Local Decoupling
Zhenyu Yang, Gensheng Pei, Tao Chen +4
Modern vision models must capture image-level context without sacrificing local detail while remaining computationally affordable. We revisit this tradeoff and advance a simple pri…
Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation
Xinhao Cai, Gensheng Pei, Zeren Sun +3
In this paper, we propose \textbf{Iris}, a deterministic framework for Monocular Depth Estimation (MDE) that integrates real-world priors into the diffusion model. Conventional fee…
PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation
Jianjian Yin, Tao Chen, Yi Chen +4
Recent advances in vision-language models (VLMs) have garnered substantial attention in open-vocabulary semantic and part segmentation (OSPS). However, existing methods extract ima…
PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection
Xinhao Cai, Liulei Li, Gensheng Pei +3
Object detection in remote sensing images (RSIs) is challenged by the coexistence of geometric and spatial complexity: targets may appear with diverse aspect ratios, while spanning…
Towards Remote Sensing Change Detection with Neural Memory
Zhenyu Yang, Gensheng Pei, Yazhou Yao +3
Remote sensing change detection is essential for environmental monitoring, urban planning, and related applications. However, current methods often struggle to capture long-range d…
Taming SAM3 in the Wild: A Concept Bank for Open-Vocabulary Segmentation
Gensheng Pei, Xiruo Jiang, Yazhou Yao +3
The recent introduction of \texttt{SAM3} has revolutionized Open-Vocabulary Segmentation (OVS) through \textit{promptable concept segmentation}, which grounds pixel predictions in…
Unbiased Object Detection Beyond Frequency with Visually Prompted Image Synthesis
Xinhao Cai, Liulei Li, Gensheng Pei +4
This paper presents a generation-based debiasing framework for object detection. Prior debiasing methods are often limited by the representation diversity of samples, while naive g…
Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning
Jianjian Yin, Tao Chen, Gensheng Pei +3
Consistency regularization has prevailed in semi-supervised semantic segmentation and achieved promising performance. However, existing methods typically concentrate on enhancing t…
Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection
Gensheng Pei, Tao Chen, Yujia Wang +4
The CLIP model has demonstrated significant advancements in aligning visual and language modalities through large-scale pre-training on image-text pairs, enabling strong zero-shot…
Relating CNN-Transformer Fusion Network for Change Detection
Yuhao Gao, Gensheng Pei, Mengmeng Sheng +3
While deep learning, particularly convolutional neural networks (CNNs), has revolutionized remote sensing (RS) change detection (CD), existing approaches often miss crucial feature…
Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation
Tao Chen, XiRuo Jiang, Gensheng Pei +3
Though adversarial erasing has prevailed in weakly supervised semantic segmentation to help activate integral object regions, existing approaches still suffer from the dilemma of u…
Universal Organizer of SAM for Unsupervised Semantic Segmentation
Tingting Li, Gensheng Pei, Xinhao Cai +3
Unsupervised semantic segmentation (USS) aims to achieve high-quality segmentation without manual pixel-level annotations. Existing USS models provide coarse category classificatio…
A Light-weight Transformer-based Self-supervised Matching Network for Heterogeneous Images
Wang Zhang, Tingting Li, Yuntian Zhang +3
Matching visible and near-infrared (NIR) images remains a significant challenge in remote sensing image fusion. The nonlinear radiometric differences between heterogeneous remote s…
Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object Segmentation
Gensheng Pei, Yazhou Yao, Jianbo Jiao +3
Conventional video object segmentation (VOS) methods usually necessitate a substantial volume of pixel-level annotated video data for fully supervised learning. In this paper, we p…
VideoMAC: Video Masked Autoencoders Meet ConvNets
Gensheng Pei, Tao Chen, Xiruo Jiang +3
Recently, the advancement of self-supervised learning techniques, like masked autoencoders (MAE), has greatly influenced visual representation learning for images and videos. Never…
Hierarchical Graph Pattern Understanding for Zero-Shot VOS
Gensheng Pei, Fumin Shen, Yazhou Yao +3
The optical flow guidance strategy is ideal for obtaining motion information of objects in the video. It is widely utilized in video segmentation tasks. However, existing optical f…
Co-attention Propagation Network for Zero-Shot Video Object Segmentation
Gensheng Pei, Yazhou Yao, Fumin Shen +3
Zero-shot video object segmentation (ZS-VOS) aims to segment foreground objects in a video sequence without prior knowledge of these objects. However, existing ZS-VOS methods often…
Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation
Gensheng Pei, Fumin Shen, Yazhou Yao +3
Optical flow is an easily conceived and precious cue for advancing unsupervised video object segmentation (UVOS). Most of the previous methods directly extract and fuse the motion…