Search Results for author:
Found 66 papers, 30 papers with code
Shonan Rotation Averaging: Global Optimality by Surfing SO(p)(n)
Shonan Rotation Averaging is a fast, simple, and elegant rotation averaging algorithm that is guaranteed to recover globally optimal solutions under mild assumptions on the measurement noise.
Optimizing Prompt Strategies for SAM: Advancing lesion Segmentation Across Diverse Medical Imaging Modalities
The prompt location also influenced performance, with surface and union-based prompts outperforming center-based prompts, achieving mean Dice coefficients of 0. 604 and 0. 724 for ovarian and breast tumors, respectively.
MUNBa: Machine Unlearning via Nash Bargaining
To address the gradient conflict issue, we reformulate MU as a two-player cooperative game, where the two players, namely, the forgetting player and the preservation player, contribute via their gradient proposals to maximize their overall gain.
TabDeco: A Comprehensive Contrastive Framework for Decoupled Representations in Tabular Data
Representation learning is a fundamental aspect of modern artificial intelligence, driving substantial improvements across diverse applications.
DSCformer: A Dual-Branch Network Integrating Enhanced Dynamic Snake Convolution and SegFormer for Crack Segmentation
In construction quality monitoring, accurately detecting and segmenting cracks in concrete structures is paramount for safety and maintenance.
CROPS: A Deployable Crop Management System Over All Possible State Availabilities
Exploring the optimal management strategy for nitrogen and irrigation has a significant impact on crop yield, economic profit, and the environment.
Cycle-Constrained Adversarial Denoising Convolutional Network for PET Image Denoising: Multi-Dimensional Validation on Large Datasets with Reader Study and Real Low-Dose Data
To simulate low-dose PET conditions, images were reconstructed from shortened scan durations of 30, 12, and 5 seconds, corresponding to 1/4, 1/10, and 1/24 of the full-dose acquisition, respectively, using a custom-developed GPU-based image reconstruction software.
EMOCPD: Efficient Attention-based Models for Computational Protein Design Using Amino Acid Microenvironment
It aims to predict the category of each amino acid in a protein by analyzing the three-dimensional atomic environment surrounding the amino acids, and optimize the protein based on the predicted high-probability potential amino acid categories.
RuleExplorer: A Scalable Matrix Visualization for Understanding Tree Ensemble Classifiers
To ensure the inclusion of anomalous rules, we develop an anomaly-biased model reduction method to prioritize these rules at each hierarchical level.
Efficient Large Foundation Models Design: A Perspective From Model and System Co-Design
This paper focuses on modern efficient training and inference technologies on foundation models and illustrates them from two perspectives: model and system design.
CNIMA: A Universal Evaluation Framework and Automated Approach for Assessing Second Language Dialogues
We annotate CNIMA using an evaluation framework -- originally introduced for English-as-a-second-language dialogues -- that assesses micro-level features (e. g.\ backchannels) and macro-level interactivity labels (e. g.\ topic management) and test the framework's transferability from English to Chinese.
Single-Point Supervised High-Resolution Dynamic Network for Infrared Small Target Detection
It balances network depth and feature resolution to maintain deep IR small-target information.
Fusion of Short-term and Long-term Attention for Video Mirror Detection
However, to ensure that the candidate is indeed a mirror (not a picture or a window), we often need to observe more frames for a global view.
Unraveling Radiomics Complexity: Strategies for Optimal Simplicity in Predictive Modeling
Purpose: Develop a methodology and tools to identify and explain the smallest set of predictive radiomic features.
Zero-Shot Video Editing through Adaptive Sliding Score Distillation
To address these challenges, this study proposes a novel paradigm of video-based score distillation, facilitating direct manipulation of original video content.
Multi-Level Feature Fusion Network for Lightweight Stereo Image Super-Resolution
Stereo image super-resolution utilizes the cross-view complementary information brought by the disparity effect of left and right perspective images to reconstruct higher-quality images.
Deep Representation Learning for Multi-functional Degradation Modeling of Community-dwelling Aging Population
As the aging population grows, particularly for the baby boomer generation, the United States is witnessing a significant increase in the elderly population experiencing multifunctional disabilities.
Towards a Robust Retrieval-Based Summarization System
SummRAG is an example of our goal of defining structured methods to test the capabilities of an LLM, rather than addressing issues in a one-off fashion.
DerainNeRF: 3D Scene Estimation with Adhesive Waterdrop Removal
When capturing images through the glass during rainy or snowy weather conditions, the resulting images often contain waterdrops adhered on the glass surface, and these waterdrops significantly degrade the image quality and performance of many computer vision algorithms.
The New Agronomists: Language Models are Experts in Crop Management
A novel aspect of our approach is the conversion of these state variables into more informative language, facilitating the language model's capacity to understand states and explore optimal management practices.
Residual-based Language Models are Free Boosters for Biomedical Imaging
In this study, we uncover the unexpected efficacy of residual-based large language models (LLMs) as part of encoders for biomedical imaging tasks, a domain traditionally devoid of language or textual data.
GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS).
Investigating White-Box Attacks for On-Device Models
Our findings emphasize the need for developers to carefully consider their model deployment strategies, and use white-box methods to evaluate the vulnerability of on-device models.
MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline
Large language models (LLMs) have seen considerable advancements in natural language understanding tasks, yet there remains a gap to bridge before attaining true artificial general intelligence, especially concerning shortcomings in mathematical reasoning capabilities.
Erasing Undesirable Influence in Diffusion Models
Diffusion models are highly effective at generating high-quality images but pose risks, such as the unintentional generation of NSFW (not safe for work) content.
Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks
By reinitializing the most influential top-k percent of these parameters, a trimmed model for erasing the influence of the forgetting data is obtained.
SwitchTab: Switched Autoencoders Are Effective Tabular Learners
Self-supervised representation learning methods have achieved significant success in computer vision and natural language processing, where data samples exhibit explicit spatial or semantic dependencies.
Large Scale Foundation Models for Intelligent Manufacturing Applications: A Survey
Although the applications of artificial intelligence especially deep learning had greatly improved various aspects of intelligent manufacturing, they still face challenges for wide employment due to the poor generalization ability, difficulties to establish high-quality training datasets, and unsatisfactory performance of deep learning methods.
ReConTab: Regularized Contrastive Representation Learning for Tabular Data
In response to this challenge, we introduce ReConTab, a deep automatic representation learning framework with regularized contrastive learning.
Adaptive Policy with Wait-$k$ Model for Simultaneous Translation
Simultaneous machine translation (SiMT) requires a robust read/write policy in conjunction with a high-quality translation model.
Feature Proliferation -- the "Cancer" in StyleGAN and its Treatments
Thanks to our discovery of Feature Proliferation, the proposed feature rescaling method is less destructive and retains more useful image features than the truncation trick, as it is more fine-grained and works in a lower-level feature space rather than a high-level latent space.
A Unified Interactive Model Evaluation for Classification, Object Detection, and Instance Segmentation in Computer Vision
Existing model evaluation tools mainly focus on evaluating classification models, leaving a gap in evaluating more complex models, such as object detection.
Local Consensus Enhanced Siamese Network with Reciprocal Loss for Two-view Correspondence Learning
First, we propose a Local Feature Consensus (LFC) plugin block to augment the features of existing models.
GenCo: An Auxiliary Generator from Contrastive Learning for Enhanced Few-Shot Learning in Remote Sensing
We demonstrate the effectiveness of our method in improving few-shot learning performance on two key remote sensing datasets: Agriculture-Vision and EuroSAT.
Hallucination Improves the Performance of Unsupervised Visual Representation Learning
Contrastive learning models based on Siamese structure have demonstrated remarkable performance in self-supervised learning.
Recent Advances of Deep Robotic Affordance Learning: A Reinforcement Learning Perspective
As a popular concept proposed in the field of psychology, affordance has been regarded as one of the important abilities that enable humans to understand and interact with the environment.
Extended Agriculture-Vision: An Extension of a Large Aerial Image Dataset for Agricultural Pattern Analysis
First, we generate and release an improved version of the Agriculture-Vision dataset (Chiu et al., 2020b) to include raw, full-field imagery for greater experimental flexibility.
Balanced Training for Sparse GANs
We also introduce a new method called balanced dynamic sparse training (ADAPT), which seeks to control the BR during GAN training to achieve a good trade-off between performance and computational cost.
Active Learning in Brain Tumor Segmentation with Uncertainty Sampling, Annotation Redundancy Restriction, and Data Initialization
We investigated uncertainty sampling, annotation redundancy restriction, and initial dataset selection techniques.
Optimizing Crop Management with Reinforcement Learning and Imitation Learning
Moreover, the partial-observation management policies are directly deployable in the real world as they use readily available information.
Concealing Sensitive Samples against Gradient Leakage in Federated Learning
Federated Learning (FL) is a distributed learning paradigm that enhances users privacy by eliminating the need for clients to share raw, private data with the server.
Abstract Demonstrations and Adaptive Exploration for Efficient and Stable Multi-step Sparse Reward Reinforcement Learning
Although Deep Reinforcement Learning (DRL) has been popular in many disciplines including robotics, state-of-the-art DRL algorithms still struggle to learn long-horizon, multi-step and sparse reward tasks, such as stacking several blocks given only a task-completion reward signal.
A Unified Understanding of Deep NLP Models for Text Classification
The rapid development of deep natural language processing (NLP) models for text classification has led to an urgent need for a unified understanding of these models proposed individually.
Exploring and Exploiting Hubness Priors for High-Quality GAN Latent Sampling
Despite the extensive studies on Generative Adversarial Networks (GANs), how to reliably sample high-quality images from their latent spaces remains an under-explored topic.
Optimizing Nitrogen Management with Deep Reinforcement Learning and Crop Simulations
Nitrogen (N) management is critical to sustain soil fertility and crop production while minimizing the negative environmental impact, but is challenging to optimize.
Playing Lottery Tickets in Style Transfer Models
(2) Using iterative magnitude pruning, we find the matching subnetworks at 89. 2% sparsity in AdaIN and 73. 7% sparsity in SANet, which demonstrates that style transfer models can play lottery tickets too.
An Open-Source Multi-Goal Reinforcement Learning Environment for Robotic Manipulation with Pybullet
This work re-implements the OpenAI Gym multi-goal robotic manipulation environment, originally based on the commercial Mujoco engine, onto the open-source Pybullet engine.
Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions
Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models.
A Survey On Universal Adversarial Attack
The intriguing phenomenon of adversarial examples has attracted significant attention in machine learning and what might be more surprising to the community is the existence of universal adversarial perturbations (UAPs), i. e. a single perturbation to fool the target DNN for most images.
Tunable Doping of Rhenium and Vanadium into Transition Metal Dichalcogenides for Two-Dimensional Electronics
Alternatively, using highly conductive doped TMDCs will have a profound impact on the contact engineering of 2D electronics.
Materials Science
VENet: Voting Enhancement Network for 3D Object Detection
Hough voting, as has been demonstrated in VoteNet, is effective for 3D object detection, where voting is a key step.
MLVSNet: Multi-Level Voting Siamese Network for 3D Visual Tracking
To deal with sparsity in outdoor 3D point clouds, we propose to perform Hough voting on multi-level features to get more vote centers and retain more useful information, instead of voting only on the final level feature as in previous methods.
Network Hawkes Process Models for Exploring Latent Hierarchy in Social Animal Interactions
We compare all models using simulated and real data.
Applications Methodology
A Generalized Robotic Handwriting Learning System based on Dynamic Movement Primitives (DMPs)
Learning from demonstration (LfD) is a powerful learning method to enable a robot to infer how to perform a task given one or more human demonstrations of the desired task.
Robotics
Decision-based Universal Adversarial Attack
A single perturbation can pose the most natural images to be misclassified by classifiers.
Shonan Rotation Averaging: Global Optimality by Surfing $SO(p)^n$
Shonan Rotation Averaging is a fast, simple, and elegant rotation averaging algorithm that is guaranteed to recover globally optimal solutions under mild assumptions on the measurement noise.
$E^3$: Visual Exploration of Spatiotemporal Energy Demand
Understanding demand-side energy behaviour is critical for making efficiency responses for energy demand management.
Human-Computer Interaction Computers and Society
Manifold Alignment for Semantically Aligned Style Transfer
In this paper, we make a new assumption that image features from the same semantic region form a manifold and an image with multiple semantic regions follows a multi-manifold distribution.
ProbaNet: Proposal-balanced Network for Object Detection
Candidate object proposals generated by object detectors based on convolutional neural network (CNN) encounter easy-hard samples imbalance problem, which can affect overall performance.
MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
We demonstrate these by capturing contextual information at patch, object and scene levels.
Ranked #2 on
3D Object Detection
on ARKitScenes
DaST: Data-free Substitute Training for Adversarial Attacks
In this paper, we propose a data-free substitute training method (DaST) to obtain substitute models for adversarial black-box attacks without the requirement of any real data.
Adversarial Imitation Attack
Then, the adversarial examples generated by the imitation model are utilized to fool the attacked model.
Analyzing the Noise Robustness of Deep Neural Networks
The key is to compare and analyze the datapaths of both the adversarial and normal examples.
MW-GAN: Multi-Warping GAN for Caricature Generation with Multi-Style Geometric Exaggeration
Given an input face photo, the goal of caricature generation is to produce stylized, exaggerated caricatures that share the same identity as the photo.
Rigid Point Registration with Expectation Conditional Maximization
This paper addresses the issue of matching rigid 3D object points with 2D image points through point registration based on maximum likelihood principle in computer simulated images.
