28 citations · 68 across the 19 of their papers we have counts for
20 papers
MaskMed: Decoupled Mask and Class Prediction for Medical Image Segmentation
Bin Xie, Gady Agam
Medical image segmentation typically adopts a point-wise convolutional segmentation head to predict dense labels, where each output channel is heuristically tied to a specific clas…
MSLoRA: Multi-Scale Low-Rank Adaptation via Attention Reweighting
Xu Yang, Gady Agam
We introduce MSLoRA, a backbone-agnostic, parameter-efficient adapter that reweights feature responses rather than re-tuning the underlying backbone. Existing low-rank adaptation m…
Motion-Aware Transformer for Multi-Object Tracking
Xu Yang, Gady Agam
Multi-object tracking (MOT) in videos remains challenging due to complex object motions and crowded scenes. Recent DETR-based frameworks offer end-to-end solutions but typically pr…
MM-UNet: Meta Mamba UNet for Medical Image Segmentation
Bin Xie, Yan Yan, Gady Agam
State Space Models (SSMs) have recently demonstrated outstanding performance in long-sequence modeling, particularly in natural language processing. However, their direct applicati…
RFMedSAM 2: Automatic Prompt Refinement for Enhanced Volumetric Medical Image Segmentation with SAM 2
Bin Xie, Hao Tang, Yan Yan +1
Segment Anything Model 2 (SAM 2), a prompt-driven foundation model extending SAM to both image and video domains, has shown superior zero-shot performance compared to its predecess…
Rethinking Timesteps Samplers and Prediction Types
Bin Xie, Gady Agam
Diffusion models suffer from the huge consumption of time and resources to train. For example, diffusion models need hundreds of GPUs to train for several weeks for a high-resoluti…
Self-Prompt SAM: Medical Image Segmentation via Automatic Prompt SAM Adaptation
Bin Xie, Hao Tang, Dawen Cai +2
Segment Anything Model (SAM) has demonstrated impressive zero-shot performance and brought a range of unexplored capabilities to natural image segmentation tasks. However, as a ver…
Fine-grained Text to Image Synthesis
Xu Ouyang, Ying Chen, Kaiyue Zhu +1
Fine-grained text to image synthesis involves generating images from texts that belong to different categories. In contrast to general text to image synthesis, in fine-grained synt…
MaskSAM: Towards Auto-prompt SAM with Mask Classification for Volumetric Medical Image Segmentation
Bin Xie, Hao Tang, Bin Duan +3
Segment Anything Model (SAM), a prompt-driven foundation model for natural image segmentation, has demonstrated impressive zero-shot performance. However, SAM does not work when di…
LSTM Framework for Classification of Radar and Communications Signals
Victoria Clerico, Jorge Gonzalez-Lopez, Gady Agam +1
Although radar and communications signal classification are usually treated separately, they share similar characteristics, and methods applied in one domain can be potentially app…
Semi-supervised Domain Adaptation for Semantic Segmentation
Ying Chen, Xu Ouyang, Kaiyue Zhu +1
Deep learning approaches for semantic segmentation rely primarily on supervised learning approaches and require substantial efforts in producing pixel-level annotations. Further, s…
Mask-based Data Augmentation for Semi-supervised Semantic Segmentation
Ying Chen, Xu Ouyang, Kaiyue Zhu +1
Semantic segmentation using convolutional neural networks (CNN) is a crucial component in image analysis. Training a CNN to perform semantic segmentation requires a large amount of…
Domain Adaptation on Semantic Segmentation for Aerial Images
Ying Chen, Xu Ouyang, Kaiyue Zhu +1
Semantic segmentation has achieved significant advances in recent years. While deep neural networks perform semantic segmentation well, their success rely on pixel level supervisio…
Accelerated WGAN update strategy with loss change rate balancing
Xu Ouyang, Gady Agam
Optimizing the discriminator in Generative Adversarial Networks (GANs) to completion in the inner training loop is computationally prohibitive, and on finite datasets would result…
Generating Image Sequence from Description with LSTM Conditional GAN
Xu Ouyang, Xi Zhang, Di Ma +1
Generating images from word descriptions is a challenging task. Generative adversarial networks(GANs) are shown to be able to generate realistic images of real-life objects. In thi…
Layered Optical Flow Estimation Using a Deep Neural Network with a Soft Mask
Xi Zhang, Di Ma, Xu Ouyang +3
Using a layered representation for motion estimation has the advantage of being able to cope with discontinuities and occlusions. In this paper, we learn to estimate optical flow b…
Lecture video indexing using boosted margin maximizing neural networks
Di Ma, Xi Zhang, Xu Ouyang +1
This paper presents a novel approach for lecture video indexing using a boosted deep convolutional neural network system. The indexing is performed by matching high quality slide i…
CGMOS: Certainty Guided Minority OverSampling
Xi Zhang, Di Ma, Lin Gan +2
Handling imbalanced datasets is a challenging problem that if not treated correctly results in reduced classification performance. Imbalanced datasets are commonly handled using mi…
Learning from Synthetic Data Using a Stacked Multichannel Autoencoder
Xi Zhang, Yanwei Fu, Shanshan Jiang +2
Learning from synthetic data has many important and practical applications. An example of application is photo-sketch recognition. Using synthetic data is challenging due to the di…
Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder
Xi Zhang, Yanwei Fu, Andi Zang +2
We propose a method for using synthetic data to help learning classifiers. Synthetic data, even is generated based on real data, normally results in a shift from the distribution o…