Search Results for author:
Found 76 papers, 34 papers with code
Towards Training-Free Open-World Classification with 3D Generative Models
3D open-world classification is a challenging yet essential task in dynamic and unstructured real-world scenarios, requiring both open-category and open-pose recognition.
Efficient Interactive 3D Multi-Object Removal
Object removal is of great significance to 3D scene understanding, essential for applications in content filtering and scene editing.
Consistency Diffusion Models for Single-Image 3D Reconstruction with Priors
First, we convert 3D structural priors derived from the initial 3D point cloud as a bound term to increase evidence in the variational Bayesian framework, leveraging these robust intrinsic priors to tightly govern the diffusion training process and bolster consistency in reconstruction.
IDEA: Image Description Enhanced CLIP-Adapter
As one important contribution, we employ the Llama model and design a comprehensive pipeline to generate textual descriptions for images of 11 datasets, resulting in a total of 1, 637, 795 image-text pairs, named "IMD-11".
Discrete Wavelet Transform-Based Capsule Network for Hyperspectral Image Classification
Hyperspectral image (HSI) classification is a crucial technique for remote sensing to build large-scale earth monitoring systems.
Improved Feature Generating Framework for Transductive Zero-shot Learning
This paper delves into the pivotal influence of unseen class priors within the framework of transductive ZSL (TZSL) and illuminates the finding that even a marginal prior bias can result in substantial accuracy declines.
Template-Driven LLM-Paraphrased Framework for Tabular Math Word Problem Generation
In this paper, we propose a Template-driven LLM-paraphrased (TeLL) framework for generating high-quality TMWP samples with diverse backgrounds and accurate tables, questions, answers, and solutions.
PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection
Point cloud anomaly detection under the anomaly-free setting poses significant challenges as it requires accurately capturing the features of 3D normal data to identify deviations indicative of anomalies.
Towards Cross-device and Training-free Robotic Grasping in 3D Open World
Leveraging the segmentation results, we propose to engage a training-free binary clustering algorithm that not only improves segmentation precision but also possesses the capability to cluster and localize unseen objects for executing grasping operations.
A comprehensive survey of oracle character recognition: challenges, benchmarks, and beyond
Oracle character recognition-an analysis of ancient Chinese inscriptions found on oracle bones-has become a pivotal field intersecting archaeology, paleography, and historical cultural studies.
Decentralizing Test-time Adaptation under Heterogeneous Data Streams
While Test-Time Adaptation (TTA) has shown promise in addressing distribution shifts between training and testing data, its effectiveness diminishes with heterogeneous data streams due to uniform target estimation.
Disentangling Tabular Data Towards Better One-Class Anomaly Detection
To our knowledge, this is a pioneering effort to apply the concept of disentanglement for one-class anomaly detection on tabular data.
Personalize to generalize: Towards a universal medical multi-modality generalization through personalization
We validate the feasibility and benefits of learning a personalized ${X}_h$, showing that this representation is highly generalizable and transferable across various multi-modal medical tasks.
Navigating Distribution Shifts in Medical Image Analysis: A Survey
Medical Image Analysis (MedIA) has become indispensable in modern healthcare, enhancing clinical diagnostics and personalized treatment.
Covariance-based Space Regularization for Few-shot Class Incremental Learning
In this paper, we aim to mitigate these issues by directly constraining the span of each class distribution from a covariance perspective.
class-incremental learning
Few-Shot Class-Incremental Learning
+1
Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual Classification
Vision models excel in image classification but struggle to generalize to unseen data, such as classifying images from unseen domains or discovering novel categories.
Mind the Gap: Promoting Missing Modality Brain Tumor Segmentation with Alignment
Brain tumor segmentation is often based on multiple magnetic resonance imaging (MRI).
CathAction: A Benchmark for Endovascular Intervention Understanding
Real-time visual feedback from catheterization analysis is crucial for enhancing surgical safety and efficiency during endovascular interventions.
EEG-Defender: Defending against Jailbreak through Early Exit Generation of Large Language Models
Large Language Models (LLMs) are increasingly attracting attention in various applications.
MedMAP: Promoting Incomplete Multi-modal Brain Tumor Segmentation with Alignment
Along this line, in this paper, we propose a novel paradigm that aligns latent features of involved modalities to a well-defined distribution anchor as the substitution of the pre-trained model}.
W-Net: One-Shot Arbitrary-Style Chinese Character Generation with Deep Neural Networks
Due to the huge category number, the sophisticated combinations of various strokes and radicals, and the free writing or printing styles, generating Chinese characters with diverse styles is always considered as a difficult task.
Generalized W-Net: Arbitrary-style Chinese Character Synthesization
Synthesizing Chinese characters with consistent style using few stylized examples is challenging.
Exploring Data Efficiency in Zero-Shot Learning with Diffusion Models
For class-level effectiveness, we design a two-branch generation structure that consists of a Diffusion-based Feature Generator (DFG) and a Diffusion-based Representation Generator (DRG).
Ranked #1 on
Zero-Shot Learning
on AwA2
Revisiting Mutual Information Maximization for Generalized Category Discovery
Generalized category discovery presents a challenge in a realistic scenario, which requires the model's generalization ability to recognize unlabeled samples from known and unknown categories.
SCMix: Stochastic Compound Mixing for Open Compound Domain Adaptation in Semantic Segmentation
Built upon this, we argue that conventional OCDA approaches may substantially underestimate the inherent variance inside the compound target domains for model generalization.
DKE-Research at SemEval-2024 Task 2: Incorporating Data Augmentation with Generative Models and Biomedical Knowledge to Enhance Inference Robustness
Safe and reliable natural language inference is critical for extracting insights from clinical trial reports but poses challenges due to biases in large pre-trained language models.
Rethinking Information Loss in Medical Image Segmentation with Various-sized Targets
Medical image segmentation presents the challenge of segmenting various-size targets, demanding the model to effectively capture both local and global information.
Rethinking Multi-domain Generalization with A General Learning Objective
Multi-domain generalization (mDG) is universally aimed to minimize the discrepancy between training and testing distributions to enhance marginal-to-label distribution mapping.
Ranked #2 on
Domain Generalization
on TerraIncognita
Rethinking Spectral Graph Neural Networks with Spatially Adaptive Filtering
Whilst spectral Graph Neural Networks (GNNs) are theoretically well-founded in the spectral domain, their practical reliance on polynomial approximation implies a profound linkage to the spatial domain.
Diff-Oracle: Deciphering Oracle Bone Scripts with Controllable Diffusion Model
In particular, on the challenging OBC306 dataset, Diff-Oracle leads to an accuracy gain of 7. 70% in the zero-shot setting and is able to recognize unseen oracle character images with the accuracy of 84. 62%, achieving a new benchmark for deciphering oracle bone scripts.
Unraveling Batch Normalization for Realistic Test-Time Adaptation
While recent test-time adaptations exhibit efficacy by adjusting batch normalization to narrow domain disparities, their effectiveness diminishes with realistic mini-batches due to inaccurate target estimation.
Graph Neural Networks with Diverse Spectral Filtering
Spectral Graph Neural Networks (GNNs) have achieved tremendous success in graph machine learning, with polynomial filters applied for graph convolutions, where all nodes share the identical filter weights to mine their local contexts.
Polar-Doc: One-Stage Document Dewarping with Multi-Scope Constraints under Polar Representation
While Cartesian coordinates are typically leveraged by state-of-the-art approaches to learn a group of deformation control points, such representation is not efficient for dewarping model to learn the deformation information.
Semantic-aware Data Augmentation for Text-to-image Synthesis
In particular, we propose to augment texts in the semantic space via an Implicit Textual Semantic Preserving Augmentation ($ITA$), in conjunction with a specifically designed Image Semantic Regularization Loss ($L_r$) as Generated Image Semantic Conservation, to cope well with semantic mismatch and collapse.
Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges
To this end, we propose a more realistic and challenging scenario named open-pose 3D zero-shot classification, focusing on the recognition of 3D objects regardless of their orientation.
Zero-Shot Medical Information Retrieval via Knowledge Graph Embedding
In the era of the Internet of Things (IoT), the retrieval of relevant medical information has become essential for efficient clinical decision-making.
Context Does Matter: End-to-end Panoptic Narrative Grounding with Deformable Attention Refined Matching Network
The current state-of-the-art methods first refine the representation of phrase by aggregating the most similar $k$ image pixels, and then match the refined text representations with the pixels of the image feature map to generate segmentation results.
MathAttack: Attacking Large Language Models Towards Math Solving Ability
Instead of attacking prompts in the use of LLMs, we propose a MathAttack model to attack MWP samples which are closer to the essence of security in solving math problems.
A Symbolic Character-Aware Model for Solving Geometry Problems
For the diagram encoder, we pre-train it under a multi-label classification framework with the symbolic characters as labels.
Learning by Analogy: Diverse Questions Generation in Math Word Problem
We then feed them to a question generator together with the scenario to obtain the corresponding diverse questions, forming a new MWP with a variety of questions and equations.
SaliencyCut: Augmenting Plausible Anomalies for Anomaly Detection
We then design a novel patch-wise residual module in the anomaly learning head to extract and assess the fine-grained anomaly features from each sample, facilitating the learning of discriminative representations of anomaly instances.
Can Perturbations Help Reduce Investment Risks? Risk-Aware Stock Recommendation via Split Variational Adversarial Training
By lowering the volatility of the stock recommendation model, SVAT effectively reduces investment risks and outperforms state-of-the-art baselines by more than 30% in terms of risk-adjusted profits.
A generalizable framework for low-rank tensor completion with numerical priors
We present the Generalized CP Decomposition Tensor Completion (GCDTC) framework, the first generalizable framework for low-rank tensor completion that takes numerical priors of the data into account.
Towards Better Robustness against Common Corruptions for Unsupervised Domain Adaptation
Recent studies have investigated how to achieve robustness for unsupervised domain adaptation (UDA).
Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation
On the one hand, the unidirectional projection enforces our model focused more on the core task, i. e., 3D segmentation; on the other hand, unlocking the bidirectional to unidirectional projection enables a deeper cross-domain semantic alignment and enjoys the flexibility to fuse better and complicated features from very different spaces.
Deep Learning for Brain Age Estimation: A Systematic Review
In this review, we offer a comprehensive analysis of the literature related to the adoption of deep learning for brain age estimation with neuroimaging data.
Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image Segmentation
Single-source domain generalization (SDG) in medical image segmentation is a challenging yet essential task as domain shifts are quite common among clinical image datasets.
SSD: Towards Better Text-Image Consistency Metric in Text-to-Image Generation
Generating consistent and high-quality images from given texts is essential for visual-language understanding.
Rebalanced Zero-shot Learning
Broadly speaking, present ZSL methods usually adopt class-level semantic labels and compare them with instance-level semantic predictions to infer unseen classes.
EgPDE-Net: Building Continuous Neural Networks for Time Series Prediction with Exogenous Variables
While exogenous variables have a major impact on performance improvement in time series analysis, inter-series correlation and time dependence among them are rarely considered in the present continuous methods.
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization
Due to the uneven distribution of offset points, these existing methods can hardly cluster all instance points.
Ranked #3 on
3D Instance Segmentation
on S3DIS
Outpainting by Queries
Image outpainting, which is well studied with Convolution Neural Network (CNN) based framework, has recently drawn more attention in computer vision.
ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting
While Graph Neural Networks (GNNs) have achieved enormous success in multiple graph analytical tasks, modern variants mostly rely on the strong inductive bias of homophily.
Mind The Gap: Alleviating Local Imbalance for Unsupervised Cross-Modality Medical Image Segmentation
This combination of global and local alignment can precisely localize the crucial regions in segmentation target while preserving the overall semantic consistency.
From 2D Images to 3D Model:Weakly Supervised Multi-View Face Reconstruction with Deep Fusion
Specifically, we present a novel multi-view feature fusion backbone that utilizes face masks to align features from multiple encoders and integrates one multi-layer attention mechanism to enhance feature interaction and fusion, resulting in one unified facial representation.
A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologies
In this paper, we present a comprehensive survey trying to offer a systematic and structured investigation on robust adversarial training in pattern recognition.
Towards Simple and Accurate Human Pose Estimation with Stair Network
In this paper, we focus on tackling the precise keypoint coordinates regression task.
Generalised Image Outpainting with U-Transformer
In this paper, we develop a novel transformer-based generative adversarial neural network called U-Transformer for generalised image outpainting problem.
PointNu-Net: Keypoint-assisted Convolutional Neural Network for Simultaneous Multi-tissue Histology Nuclei Segmentation and Classification
Automatic nuclei segmentation and classification play a vital role in digital pathology.
Ranked #4 on
Multi-tissue Nucleus Segmentation
on CoNSeP
Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing
Sentence-based Image Editing (SIE) aims to deploy natural language to edit an image.
Perturbation Diversity Certificates Robust Generalisation
It is possibly due to the fact that the conventional adversarial training methods generate adversarial perturbations usually in a supervised way, so that the adversarial samples are highly biased towards the decision boundary, resulting in an inhomogeneous data distribution.
AD-GAN: End-to-end Unsupervised Nuclei Segmentation with Aligned Disentangling Training
We also propose a novel training algorithm able to align the disentangled content in the latent space to reduce micro-level lossy transformation.
Improving Model Robustness with Latent Distribution Locally and Globally
The proposed adversarial training with latent distribution (ATLD) method defends against adversarial attacks by crafting LMAEs with the latent manifold in an unsupervised manner.
Disentangling Semantic-to-visual Confusion for Zero-shot Learning
However, the traditional TL cannot search reliable unseen disentangled representations due to the unavailability of unseen classes in ZSL.
Structure First Detail Next: Image Inpainting with Pyramid Generator
Recent deep generative models have achieved promising performance in image inpainting.
Reborn Mechanism: Rethinking the Negative Phase Information Flow in Convolutional Neural Network
This paper proposes a novel nonlinear activation mechanism typically for convolutional neural network (CNN), named as reborn mechanism.
FastAdaBelief: Improving Convergence Rate for Belief-based Adaptive Optimizers by Exploiting Strong Convexity
%on how to exploit strong convexity to further improve the convergence rate of AdaBelief.
LGD-GCN: Local and Global Disentangled Graph Convolutional Networks
}, we introduce a novel Local and Global Disentangled Graph Convolutional Network (LGD-GCN) to capture both local and global information for graph disentanglement.
Partial Differential Equations is All You Need for Generating Neural Architectures -- A Theory for Physical Artificial Intelligence Systems
In this work, we generalize the reaction-diffusion equation in statistical physics, Schr\"odinger equation in quantum mechanics, Helmholtz equation in paraxial optics into the neural partial differential equations (NPDE), which can be considered as the fundamental equations in the field of artificial intelligence research.
Gradient Distribution Alignment Certificates Better Adversarial Domain Adaptation
In particular, we show that the distribution discrepancy can be reduced by constraining feature gradients of two domains to have similar distributions.
Explainable Tensorized Neural Ordinary Differential Equations forArbitrary-step Time Series Prediction
We propose a continuous neural network architecture, termed Explainable Tensorized Neural Ordinary Differential Equations (ETN-ODE), for multi-step time series prediction at arbitrary time points.
Global-aware Beam Search for Neural Abstractive Summarization
A global scoring mechanism is then developed to regulate beam search to generate summaries in a near-global optimal fashion.
W-Net : One-Shot Arbitrary-StyleChinese Character Generationwith Deep Neural Networks
Due to the huge category number, the sophisticated com-binations of various strokes and radicals, and the free writing or print-ing styles, generating Chinese characters with diverse styles is alwaysconsidered as a difficult task.
A Scalable Deep Neural Network Architecture for Multi-Building and Multi-Floor Indoor Localization Based on Wi-Fi Fingerprinting
Exploiting the hierarchical nature of the building/floor estimation and floor-level coordinates estimation of a location, we propose a new DNN architecture consisting of a stacked autoencoder for the reduction of feature space dimension and a feed-forward classifier for multi-label classification of building/floor/location, on which the multi-building and multi-floor indoor localization system based on Wi-Fi fingerprinting is built.
Robust Metric Learning by Smooth Optimization
Most existing distance metric learning methods assume perfect side information that is usually given in pairwise or triplet constraints.
