112 citations · 223 across the 28 of their papers we have counts for
30 papers
PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model
Wenqi Liang, Gan Sun, Yao He +5
Vision-Language-Action models (VLAs) are emerging as powerful tools for learning generalizable visuomotor control policies. However, current VLAs are mostly trained on large-scale…
MuseumMaker: Continual Style Customization without Catastrophic Forgetting
Chenxi Liu, Gan Sun, Wenqi Liang +3
Pre-trained large text-to-image (T2I) models with an appropriate text prompt has attracted growing interests in customized images generation field. However, catastrophic forgetting…
Never-Ending Behavior-Cloning Agent for Robotic Manipulation
Wenqi Liang, Gan Sun, Yao He +3
Relying on multi-modal observations, embodied robots (e.g., humanoid robots) could perform multiple robotic manipulation tasks in unstructured real-world environments. However, mos…
Create Your World: Lifelong Text-to-Image Diffusion
Gan Sun, Wenqi Liang, Jiahua Dong +3
Text-to-image generative models can produce diverse high-quality images of concepts with a text prompt, which have demonstrated excellent ability in image generation, image transla…
I3DOD: Towards Incremental 3D Object Detection via Prompting
Wenqi Liang, Gan Sun, Chenxi Liu +2
3D object detection has achieved significant performance in many fields, e.g., robotics system, autonomous driving, and augmented reality. However, most existing methods could caus…
Heterogeneous Forgetting Compensation for Class-Incremental Learning
Jiahua Dong, Wenqi Liang, Yang Cong +1
Class-incremental learning (CIL) has achieved remarkable successes in learning new classes consecutively while overcoming catastrophic forgetting on old categories. However, most e…
Task Relation Distillation and Prototypical Pseudo Label for Incremental Named Entity Recognition
Duzhen Zhang, Hongliu Li, Wei Cong +3
Incremental Named Entity Recognition (INER) involves the sequential learning of new entity types without accessing the training data of previously learned types. However, INER face…
Self-paced Weight Consolidation for Continual Learning
Wei Cong, Yang Cong, Gan Sun +2
Continual learning algorithms which keep the parameters of new tasks close to that of previous tasks, are popular in preventing catastrophic forgetting in sequential task learning…
Gradient-Semantic Compensation for Incremental Semantic Segmentation
Wei Cong, Yang Cong, Jiahua Dong +2
Incremental semantic segmentation aims to continually learn the segmentation of new coming classes without accessing the training data of previously learned classes. However, most…
Towards AI-Architecture Liberty: A Comprehensive Survey on Design and Generation of Virtual Architecture by Deep Learning
Anqi Wang, Jiahua Dong, Lik-Hang Lee +2
3D shape generation techniques leveraging deep learning have garnered significant interest from both the computer vision and architectural design communities, promising to enrich t…
Tailored Multi-Organ Segmentation with Model Adaptation and Ensemble
Jiahua Dong, Guohua Cheng, Yue Zhang +5
Multi-organ segmentation, which identifies and separates different organs in medical images, is a fundamental task in medical image analysis. Recently, the immense success of deep…
Federated Incremental Semantic Segmentation
Jiahua Dong, Duzhen Zhang, Yang Cong +3
Federated learning-based semantic segmentation (FSS) has drawn widespread attention via decentralized training on local clients. However, most FSS models assume categories are fixe…
Xformer: Hybrid X-Shaped Transformer for Image Denoising
Jiale Zhang, Yulun Zhang, Jinjin Gu +3
In this paper, we present a hybrid X-shaped vision Transformer, named Xformer, which performs notably on image denoising tasks. We explore strengthening the global representation o…
InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation
Jiahua Dong, Yang Cong, Gan Sun +4
3D object recognition has successfully become an appealing research topic in the real-world. However, most existing recognition models unreasonably assume that the categories of 3D…
No One Left Behind: Real-World Federated Class-Incremental Learning
Jiahua Dong, Hongliu Li, Yang Cong +3
Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data…
Is Out-of-Distribution Detection Learnable?
Zhen Fang, Yixuan Li, Jie Lu +3
Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studi…
BoW3D: Bag of Words for Real-Time Loop Closing in 3D LiDAR SLAM
Yunge Cui, Xieyuanli Chen, Yinlong Zhang +3
Loop closing is a fundamental part of simultaneous localization and mapping (SLAM) for autonomous mobile systems. In the field of visual SLAM, bag of words (BoW) has achieved great…
LinK3D: Linear Keypoints Representation for 3D LiDAR Point Cloud
Yunge Cui, Yinlong Zhang, Jiahua Dong +3
Feature extraction and matching are the basic parts of many robotic vision tasks, such as 2D or 3D object detection, recognition, and registration. As is known, 2D feature extracti…
IDEAL: Query-Efficient Data-Free Learning from Black-box Models
Jie Zhang, Chen Chen, Lingjuan Lyu
Knowledge Distillation (KD) is a typical method for training a lightweight student model with the help of a well-trained teacher model. However, most KD methods require access to e…
Federated Class-Incremental Learning
Jiahua Dong, Lixu Wang, Zhen Fang +4
Federated learning (FL) has attracted growing attention via data-private collaborative training on decentralized clients. However, most existing methods unrealistically assume obje…
Exploring the Equivalence of Siamese Self-Supervised Learning via A Unified Gradient Framework
Chenxin Tao, Honghui Wang, Xizhou Zhu +4
Self-supervised learning has shown its great potential to extract powerful visual representations without human annotations. Various works are proposed to deal with self-supervised…
Unsupervised Dense Deformation Embedding Network for Template-Free Shape Correspondence
Ronghan Chen, Yang Cong, Jiahua Dong
Shape correspondence from 3D deformation learning has attracted appealing academy interests recently. Nevertheless, current deep learning based methods require the supervision of d…
I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting
Jiahua Dong, Yang Cong, Gan Sun +2
3D object classification has attracted appealing attentions in academic researches and industrial applications. However, most existing methods need to access the training data of p…
Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation
Jiahua Dong, Yang Cong, Gan Sun +3
Weakly-supervised learning has attracted growing research attention on medical lesions segmentation due to significant saving in pixel-level annotation cost. However, 1) most exist…