Search Results for author:
Found 33 papers, 14 papers with code
Never-Ending Embodied Robot Learning
Relying on large language models (LLMs), embodied robots could perform complex multimodal robot manipulation tasks from visual observations with powerful generalization ability.
Federated Learning with New Knowledge: Fundamentals, Advances, and Futures
Federated Learning (FL) is a privacy-preserving distributed learning approach that is rapidly developing in an era where privacy protection is increasingly valued.
ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields
In addition to the implicit neural radiance field (NeRF) modeling, our key insight is to exploit two sources of regularization that explicitly propagate the editing information across different views, thus ensuring multi-view consistency.
MM-LLMs: Recent Advances in MultiModal Large Language Models
In the past year, MultiModal Large Language Models (MM-LLMs) have undergone substantial advancements, augmenting off-the-shelf LLMs to support MM inputs or outputs via cost-effective training strategies.
Federated Continual Novel Class Learning
In a privacy-focused era, Federated Learning (FL) has emerged as a promising machine learning technique.
Continual Named Entity Recognition without Catastrophic Forgetting
This issue is intensified in CNER due to the consolidation of old entity types from previous steps into the non-entity type at each step, leading to what is known as the semantic shift problem of the non-entity type.
Continual Named Entity Recognition
named-entity-recognition
+1
Create Your World: Lifelong Text-to-Image Diffusion
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.
I3DOD: Towards Incremental 3D Object Detection via Prompting
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.
Task Relation Distillation and Prototypical Pseudo Label for Incremental Named Entity Recognition
However, INER faces the challenge of catastrophic forgetting specific for incremental learning, further aggravated by background shift (i. e., old and future entity types are labeled as the non-entity type in the current task).
Heterogeneous Forgetting Compensation for Class-Incremental Learning
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.
Gradient-Semantic Compensation for Incremental Semantic Segmentation
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.
Self-paced Weight Consolidation for Continual Learning
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.
Towards AI-Architecture Liberty: A Comprehensive Survey on Designing and Collaborating Virtual Architecture by Deep Learning in the Metaverse
This survey investigates the latest approaches to 3D object generation with deep generative models (DGMs) and summarizes four characteristics of deep-learning generation approaches for virtual architecture.
Tailored Multi-Organ Segmentation with Model Adaptation and Ensemble
Multi-organ segmentation, which identifies and separates different organs in medical images, is a fundamental task in medical image analysis.
Federated Incremental Semantic Segmentation
Moreover, new clients collecting novel classes may join in the global training of FSS, which further exacerbates catastrophic forgetting.
Xformer: Hybrid X-Shaped Transformer for Image Denoising
The channel-wise Transformer block performs direct global context interactions across tokens defined by channel dimension.
InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation
Moreover, they cannot explore which 3D geometric characteristics are essential to alleviate the catastrophic forgetting on old classes of 3D objects.
No One Left Behind: Real-World Federated Class-Incremental Learning
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.
Is Out-of-Distribution Detection Learnable?
Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
BoW3D: Bag of Words for Real-Time Loop Closing in 3D LiDAR SLAM
To address this limitation, we present a novel Bag of Words for real-time loop closing in 3D LiDAR SLAM, called BoW3D.
LinK3D: Linear Keypoints Representation for 3D LiDAR Point Cloud
Feature extraction and matching are the basic parts of many robotic vision tasks, such as 2D or 3D object detection, recognition, and registration.
Federated Class-Incremental Learning
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.
Exploring the Equivalence of Siamese Self-Supervised Learning via A Unified Gradient Framework
These methods appear to be quite different in the designed loss functions from various motivations.
Confident Anchor-Induced Multi-Source Free Domain Adaptation
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.
Unsupervised Dense Deformation Embedding Network for Template-Free Shape Correspondence
Shape correspondence from 3D deformation learning has attracted appealing academy interests recently.
Generative Partial Visual-Tactile Fused Object Clustering
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.
I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting
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.
Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation
Weakly-supervised learning has attracted growing research attention on medical lesions segmentation due to significant saving in pixel-level annotation cost.
CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation
Unsupervised domain adaptation without consuming annotation process for unlabeled target data attracts appealing interests in semantic segmentation.
Evolving Metric Learning for Incremental and Decremental Features
Online metric learning has been widely exploited for large-scale data classification due to the low computational cost.
What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation
Unsupervised domain adaptation has attracted growing research attention on semantic segmentation.
Data Poisoning Attacks on Federated Machine Learning
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.
Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation
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.
