no code implementations • 1 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.
no code implementations • 8 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.
no code implementations • 24 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.
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.
no code implementations • 20 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.
no code implementations • 20 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.
no code implementations • 20 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.
2 code implementations • 2 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.
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.
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.
no code implementations • 28 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.
no code implementations • 16 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.
no code implementations • 8 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.
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.
no code implementations • 27 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.
no code implementations • CVPR 2020 • Jiahua Dong, Yang Cong, Gan Sun, Bineng Zhong, Xiaowei Xu
Unsupervised domain adaptation has attracted growing research attention on semantic segmentation.
no code implementations • 19 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.
no code implementations • 12 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.
no code implementations • 27 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.
no code implementations • 21 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.
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.
no code implementations • 6 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.
no code implementations • 3 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.