Search Results for author:
Found 30 papers, 15 papers with code
From Gaze to Insight: Bridging Human Visual Attention and Vision Language Model Explanation for Weakly-Supervised Medical Image Segmentation
To implement this, the teacher model first learns from gaze points enhanced by VLM-generated descriptions of lesion morphology, establishing a foundation for guiding the student model.
ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation
Recent advances in zero-shot text-to-3D generation have revolutionized 3D content creation by enabling direct synthesis from textual descriptions.
FMDConv: Fast Multi-Attention Dynamic Convolution via Speed-Accuracy Trade-off
Spatial convolution is fundamental in constructing deep Convolutional Neural Networks (CNNs) for visual recognition.
FedSCA: Federated Tuning with Similarity-guided Collaborative Aggregation for Heterogeneous Medical Image Segmentation
Transformer-based foundation models (FMs) have recently demonstrated remarkable performance in medical image segmentation.
Asynchronous Personalized Federated Learning through Global Memorization
The proliferation of Internet of Things devices and advances in communication technology have unleashed an explosion of personal data, amplifying privacy concerns amid stringent regulations like GDPR and CCPA.
Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields
To achieve this, we introduce an adapter module and mitigate the noise issue in the dense CLIP feature distillation process through a self-cross-training strategy.
SP-SLAM: Neural Real-Time Dense SLAM With Scene Priors
In this paper, we introduce SP-SLAM, a novel neural RGB-D SLAM system that performs tracking and mapping in real-time.
Simultaneous Localization and Mapping
Surface Reconstruction
Exemplar-condensed Federated Class-incremental Learning
We propose Exemplar-Condensed federated class-incremental learning (ECoral) to distil the training characteristics of real images from streaming data into informative rehearsal exemplars.
NoiseHGNN: Synthesized Similarity Graph-Based Neural Network For Noised Heterogeneous Graph Representation Learning
For homogeneous graphs, the latest works use original node features to synthesize a similarity graph that can correct the structure of the noised graph.
ErasableMask: A Robust and Erasable Privacy Protection Scheme against Black-box Face Recognition Models
Moreover, ErasableMask also exhibits outstanding perturbation erasion performance, achieving over 90% erasion success rate.
Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks
Additionally, we found that a budgeted dimension of inner optimization for the target model may contribute to the trade-off between clean accuracy and robust accuracy.
Prototype Correlation Matching and Class-Relation Reasoning for Few-Shot Medical Image Segmentation
Specifically, in order to address false pixel correlation match brought by large intra-class variations, we propose a prototype correlation matching module to mine representative prototypes that can characterize diverse visual information of different appearances well.
Wearable-based behaviour interpolation for semi-supervised human activity recognition
While traditional feature engineering for Human Activity Recognition (HAR) involves a trial-anderror process, deep learning has emerged as a preferred method for high-level representations of sensor-based human activities.
ExactDreamer: High-Fidelity Text-to-3D Content Creation via Exact Score Matching
Furthermore, to effectively capture the dynamic changes of the original and auxiliary variables, the LoRA of a pre-trained diffusion model implements these exact paths.
Rehearsal-free Federated Domain-incremental Learning
A key feature of RefFiL is the generation of local fine-grained prompts by our domain adaptive prompt generator, which effectively learns from local domain knowledge while maintaining distinctive boundaries on a global scale.
Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching
In this work, we propose a novel Trajectory Score Matching (TSM) method that aims to solve the pseudo ground truth inconsistency problem caused by the accumulated error in Interval Score Matching (ISM) when using the Denoising Diffusion Implicit Models (DDIM) inversion process.
From Sora What We Can See: A Survey of Text-to-Video Generation
With impressive achievements made, artificial intelligence is on the path forward to artificial general intelligence.
Sentinel-Guided Zero-Shot Learning: A Collaborative Paradigm without Real Data Exposure
With increasing concerns over data privacy and model copyrights, especially in the context of collaborations between AI service providers and data owners, an innovative SG-ZSL paradigm is proposed in this work.
Pixel Sentence Representation Learning
To our knowledge, this is the first representation learning method devoid of traditional language models for understanding sentence and document semantics, marking a stride closer to human-like textual comprehension.
ConRF: Zero-shot Stylization of 3D Scenes with Conditioned Radiation Fields
Most of the existing works on arbitrary 3D NeRF style transfer required retraining on each single style condition.
CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Video
The goal of our work is to generate high-quality novel views from monocular videos of complex and dynamic scenes.
Dual Feature Augmentation Network for Generalized Zero-shot Learning
To address these issues, we propose a novel Dual Feature Augmentation Network (DFAN), which comprises two feature augmentation modules, one for visual features and the other for semantic features.
UniHead: Unifying Multi-Perception for Detection Heads
The detection head constitutes a pivotal component within object detectors, tasked with executing both classification and localization functions.
DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume
Nevertheless, the dynamic cost volume inevitably generates extra occlusions and noise, thus we alleviate this by designing a fusion module that makes static and dynamic cost volumes compensate for each other.
Knowing the Past to Predict the Future: Reinforcement Virtual Learning
Reinforcement Learning (RL)-based control system has received considerable attention in recent decades.
Absolute Zero-Shot Learning
Considering the increasing concerns about data copyright and privacy issues, we present a novel Absolute Zero-Shot Learning (AZSL) paradigm, i. e., training a classifier with zero real data.
Semi-Supervised Crowd Counting from Unlabeled Data
Our method achieved competitive performance in semi-supervised learning approaches on these crowd counting datasets.
EfficientTDNN: Efficient Architecture Search for Speaker Recognition
Compared with hand-designed approaches, neural architecture search (NAS) appears as a practical technique in automating the manual architecture design process and has attracted increasing interest in spoken language processing tasks such as speaker recognition.
SOFA-Net: Second-Order and First-order Attention Network for Crowd Counting
To obtain the appropriate crowd representation, in this work we proposed SOFA-Net(Second-Order and First-order Attention Network): second-order statistics were extracted to retain selectivity of the channel-wise spatial information for dense heads while first-order statistics, which can enhance the feature discrimination for the heads' areas, were used as complementary information.
