Search Results for author: Gan Sun

Found 23 papers, 5 papers with code

Never-Ending Embodied Robot Learning

no code implementations1 Mar 2024 Wenqi Liang, Gan Sun, Qian He, Yu Ren, Jiahua Dong, Yang Cong

Relying on large language models (LLMs), embodied robots could perform complex multimodal robot manipulation tasks from visual observations with powerful generalization ability.

Robot Manipulation

Create Your World: Lifelong Text-to-Image Diffusion

no code implementations8 Sep 2023 Gan Sun, Wenqi Liang, Jiahua Dong, Jun Li, Zhengming Ding, Yang Cong

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 translation, etc.

Attribute Image Generation

I3DOD: Towards Incremental 3D Object Detection via Prompting

no code implementations24 Aug 2023 Wenqi Liang, Gan Sun, Chenxi Liu, Jiahua Dong, Kangru Wang

Meanwhile, the current class-incremental 3D object detection methods neglect the relationships between the object localization information and category semantic information and assume all the knowledge of old model is reliable.

3D Object Detection Autonomous Driving +3

Heterogeneous Forgetting Compensation for Class-Incremental Learning

1 code implementation ICCV 2023 Jiahua Dong, Wenqi Liang, Yang Cong, Gan Sun

To surmount the above challenges, we develop a novel Heterogeneous Forgetting Compensation (HFC) model, which can resolve heterogeneous forgetting of easy-to-forget and hard-to-forget old categories from both representation and gradient aspects.

Class Incremental Learning Incremental Learning +1

Gradient-Semantic Compensation for Incremental Semantic Segmentation

no code implementations20 Jul 2023 Wei Cong, Yang Cong, Jiahua Dong, Gan Sun, Henghui Ding

To tackle the above challenges, in this paper, we propose a Gradient-Semantic Compensation (GSC) model, which surmounts incremental semantic segmentation from both gradient and semantic perspectives.

Segmentation Semantic Segmentation

Self-paced Weight Consolidation for Continual Learning

no code implementations20 Jul 2023 Wei Cong, Yang Cong, Gan Sun, Yuyang Liu, Jiahua Dong

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 settings.

Continual Learning

InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation

no code implementations20 Feb 2023 Jiahua Dong, Yang Cong, Gan Sun, Lixu Wang, Lingjuan Lyu, Jun Li, Ender Konukoglu

Moreover, they cannot explore which 3D geometric characteristics are essential to alleviate the catastrophic forgetting on old classes of 3D objects.

3D Object Recognition Fairness

No One Left Behind: Real-World Federated Class-Incremental Learning

2 code implementations2 Feb 2023 Jiahua Dong, Hongliu Li, Yang Cong, Gan Sun, Yulun Zhang, Luc van Gool

These issues render global model to undergo catastrophic forgetting on old categories, when local clients receive new categories consecutively under limited memory of storing old categories.

Class Incremental Learning Federated Learning +1

Federated Class-Incremental Learning

1 code implementation CVPR 2022 Jiahua Dong, Lixu Wang, Zhen Fang, Gan Sun, Shichao Xu, Xiao Wang, Qi Zhu

It makes the global model suffer from significant catastrophic forgetting on old classes in real-world scenarios, where local clients often collect new classes continuously and have very limited storage memory to store old classes.

Class Incremental Learning Federated Learning +1

Confident Anchor-Induced Multi-Source Free Domain Adaptation

1 code implementation NeurIPS 2021 Jiahua Dong, Zhen Fang, Anjin Liu, Gan Sun, Tongliang Liu

To address these challenges, we develop a novel Confident-Anchor-induced multi-source-free Domain Adaptation (CAiDA) model, which is a pioneer exploration of knowledge adaptation from multiple source domains to the unlabeled target domain without any source data, but with only pre-trained source models.

Pseudo Label Source-Free Domain Adaptation +1

Generative Partial Visual-Tactile Fused Object Clustering

no code implementations28 Dec 2020 Tao Zhang, Yang Cong, Gan Sun, Jiahua Dong, Yuyang Liu, Zhengming Ding

More specifically, we first do partial visual and tactile features extraction from the partial visual and tactile data, respectively, and encode the extracted features in modality-specific feature subspaces.

Clustering Generative Adversarial Network +2

I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting

no code implementations16 Dec 2020 Jiahua Dong, Yang Cong, Gan Sun, Bingtao Ma, Lichen Wang

Moreover, the performance of advanced approaches degrades dramatically for past learned classes (i. e., catastrophic forgetting), due to the irregular and redundant geometric structures of 3D point cloud data.

3D Object Classification Fairness +2

Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation

no code implementations8 Dec 2020 Jiahua Dong, Yang Cong, Gan Sun, Yunsheng Yang, Xiaowei Xu, Zhengming Ding

Weakly-supervised learning has attracted growing research attention on medical lesions segmentation due to significant saving in pixel-level annotation cost.

Domain Adaptation Pseudo Label +1

CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation

no code implementations ECCV 2020 Jiahua Dong, Yang Cong, Gan Sun, Yuyang Liu, Xiaowei Xu

Unsupervised domain adaptation without consuming annotation process for unlabeled target data attracts appealing interests in semantic segmentation.

Semantic Segmentation Unsupervised Domain Adaptation

Evolving Metric Learning for Incremental and Decremental Features

no code implementations27 Jun 2020 Jiahua Dong, Yang Cong, Gan Sun, Tao Zhang, Xu Tang, Xiaowei Xu

Online metric learning has been widely exploited for large-scale data classification due to the low computational cost.

Metric Learning

Data Poisoning Attacks on Federated Machine Learning

no code implementations19 Apr 2020 Gan Sun, Yang Cong, Jiahua Dong, Qiang Wang, Ji Liu

To the end, experimental results on real-world datasets show that federated multi-task learning model is very sensitive to poisoning attacks, when the attackers either directly poison the target nodes or indirectly poison the related nodes by exploiting the communication protocol.

BIG-bench Machine Learning Data Poisoning +2

L3DOC: Lifelong 3D Object Classification

no code implementations12 Dec 2019 Yuyang Liu, Yang Cong, Gan Sun

To further transfer the task-specific knowledge from previous tasks to the new coming classification task, a memory attention mechanism is proposed to connect the current task with relevant previously tasks, which can effectively prevent catastrophic forgetting via soft-transferring previous knowledge.

3D Object Classification 3D Object Recognition +3

Lifelong Spectral Clustering

no code implementations27 Nov 2019 Gan Sun, Yang Cong, Qianqian Wang, Jun Li, Yun Fu

As a new spectral clustering task arrives, L2SC firstly transfers knowledge from both basis library and feature library to obtain encoding matrix, and further redefines the library base over time to maximize performance across all the clustering tasks.

Clustering

Visual Tactile Fusion Object Clustering

no code implementations21 Nov 2019 Tao Zhang, Yang Cong, Gan Sun, Qianqian Wang, Zhenming Ding

To effectively benefit both visual and tactile modalities for object clustering, in this paper, we propose a deep Auto-Encoder-like Non-negative Matrix Factorization framework for visual-tactile fusion clustering.

Clustering Model Optimization +1

Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation

1 code implementation ICCV 2019 Jiahua Dong, Yang Cong, Gan Sun, Dongdong Hou

To better utilize these dependencies, we present a new semantic lesions representation transfer model for weakly-supervised endoscopic lesions segmentation, which can exploit useful knowledge from relevant fully-labeled diseases segmentation task to enhance the performance of target weakly-labeled lesions segmentation task.

Pseudo Label Segmentation +2

Representative Task Self-selection for Flexible Clustered Lifelong Learning

no code implementations6 Mar 2019 Gan Sun, Yang Cong, Qianqian Wang, Bineng Zhong, Yun Fu

Consider the lifelong machine learning paradigm whose objective is to learn a sequence of tasks depending on previous experiences, e. g., knowledge library or deep network weights.

Model Optimization Multi-Task Learning

Lifelong Metric Learning

no code implementations3 May 2017 Gan Sun, Yang Cong, Ji Liu, Xiaowei Xu

In this paper, we consider lifelong learning problem to mimic "human learning", i. e., endowing a new capability to the learned metric for a new task from new online samples and incorporating previous experiences and knowledge.

Metric Learning Model Optimization

Cannot find the paper you are looking for? You can Submit a new open access paper.