Search Results for author:
Found 42 papers, 19 papers with code
Synthetic CT Generation from Time-of-Flight Non-Attenutaion-Corrected PET for Whole-Body PET Attenuation Correction
This study presents a deep learning approach to generate synthetic CT (sCT) images directly from Time-of-Flight (TOF) non-attenuation corrected (NAC) PET images, enhancing AC for PET/MR.
EasyCraft: A Robust and Efficient Framework for Automatic Avatar Crafting
We first establish a unified feature distribution in the translator's image encoder through self-supervised learning on a large-scale dataset, enabling photos of any style to be embedded into a unified feature representation.
Unbiased Evaluation of Large Language Models from a Causal Perspective
Additionally, we demonstrate that the Unbiased Evaluator not only offers strong evidence of benchmark contamination but also provides interpretable evaluation results.
Invariant debiasing learning for recommendation via biased imputation
In this paper, we experimentally demonstrate that invariant learning causes information loss by directly discarding the variant information, which reduces the generalization ability and results in the degradation of model performance in unbiased recommendations.
Versatile Volumetric Medical Image Coding for Human-Machine Vision
Neural image compression (NIC) has received considerable attention due to its significant advantages in feature representation and data optimization.
KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models
Large language models with retrieval-augmented generation encounter a pivotal challenge in intricate retrieval tasks, e. g., multi-hop question answering, which requires the model to navigate across multiple documents and generate comprehensive responses based on fragmented information.
Deep Learning for Longitudinal Gross Tumor Volume Segmentation in MRI-Guided Adaptive Radiotherapy for Head and Neck Cancer
In this study, our team, $\textit{UW LAIR}$, tackled the challenges of both pre-radiotherapy (pre-RT) (Task 1) and mid-radiotherapy (mid-RT) (Task 2) tumor volume segmentation.
SASWISE-UE: Segmentation and Synthesis with Interpretable Scalable Ensembles for Uncertainty Estimation
This paper introduces an efficient sub-model ensemble framework aimed at enhancing the interpretability of medical deep learning models, thus increasing their clinical applicability.
Deep Learning-based Detection of Bacterial Swarm Motion Using a Single Image
It blindly achieved a sensitivity of 97. 92% and a specificity of 96. 77% for DB10, and a sensitivity of 100% and a specificity of 97. 22% for H6.
Distilling Vision-Language Foundation Models: A Data-Free Approach via Prompt Diversification
In this paper, we discuss the extension of DFKD to Vision-Language Foundation Models without access to the billion-level image-text datasets.
Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers
Due to the challenges in data collection, mainstream datasets of 3D human pose estimation are primarily composed of multi-view video data collected in laboratory environments, which contains rich spatial-temporal correlation information besides the image frame content.
Parameter Exchange for Robust Dynamic Domain Generalization
The parameters of dynamic networks can be decoupled into a static and a dynamic component, which are designed to learn domain-invariant and domain-specific features, respectively.
MetaFBP: Learning to Learn High-Order Predictor for Personalized Facial Beauty Prediction
To this end, we propose a novel MetaFBP framework, in which we devise a universal feature extractor to capture the aesthetic commonality and then optimize to adapt the aesthetic individuality by shifting the decision boundary of the predictor via a meta-learning mechanism.
Adapt Anything: Tailor Any Image Classifiers across Domains And Categories Using Text-to-Image Diffusion Models
Such a one-for-all adaptation paradigm allows us to adapt anything in the world using only one text-to-image generator as well as the corresponding unlabeled target data.
Improved Cryo-EM Pose Estimation and 3D Classification through Latent-Space Disentanglement
In these methods, only a subset of the input dataset is needed to train neural networks for the estimation of poses and conformations.
FFF: Fragments-Guided Flexible Fitting for Building Complete Protein Structures
This has inspired us to combine fragment recognition and structure prediction methods to build a complete structure.
Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting
In addition, we also experiment DVP with the recently popular adapter approach to keep the most parameters of PLMs intact when adapting to VL tasks, helping PLMs achieve a quick shift between single- and multi-modal tasks.
Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations
In this paper, we present an end-to-end framework Structure-CLIP, which integrates Scene Graph Knowledge (SGK) to enhance multi-modal structured representations.
Twin support vector quantile regression
We propose a twin support vector quantile regression (TSVQR) to capture the heterogeneous and asymmetric information in modern data.
Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domains
In this work, we present an idea to remove non-causal factors from common features by multi-view adversarial training on source domains, because we observe that such insignificant non-causal factors may still be significant in other latent spaces (views) due to the multi-mode structure of data.
1st Place Solution for ECCV 2022 OOD-CV Challenge Image Classification Track
In the test-time training stage, we use the pre-trained model to assign noisy label for the unlabeled target data, and propose a Label-Periodically-Updated DivideMix method for noisy label learning.
1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection Track
The domain adaptation part is implemented as a Source-Free Domain Adaptation paradigm, which only uses the pre-trained model and the unlabeled target data to further optimize in a self-supervised training manner.
FFF: Fragment-Guided Flexible Fitting for Building Complete Protein Structures
This has inspired us to combine fragment recognition and structure prediction methods to build a complete structure.
Unsupervised Prompt Tuning for Text-Driven Object Detection
In this paper, we delve into this problem and propose an Unsupervised Prompt Tuning framework for text-driven object detection, which is composed of two novel mean teaching mechanisms.
Informing selection of performance metrics for medical image segmentation evaluation using configurable synthetic errors
By analyzing the intrinsic properties of these metrics and categorizing the segmentation errors, we are working toward the goal of developing a decision-tree tool for assisting in the selection of segmentation performance metrics.
Attention Diversification for Domain Generalization
Under this guidance, a novel Attention Diversification framework is proposed, in which Intra-Model and Inter-Model Attention Diversification Regularization are collaborated to reassign appropriate attention to diverse task-related features.
Universal Domain Adaptive Object Detector
Universal domain adaptive object detection (UniDAOD)is more challenging than domain adaptive object detection (DAOD) since the label space of the source domain may not be the same as that of the target and the scale of objects in the universal scenarios can vary dramatically (i. e, category shift and scale shift).
Unraveling the Mystery of Artifacts in Machine Generated Text
As neural Text Generation Models (TGM) have become more and more capable of generating text indistinguishable from human-written ones, the misuse of text generation technologies can have serious ramifications.
Label Matching Semi-Supervised Object Detection
To remedy this issue, we present a novel label assignment mechanism for self-training framework, namely proposal self-assignment, which injects the proposals from student into teacher and generates accurate pseudo labels to match each proposal in the student model accordingly.
Slimmable Domain Adaptation
In this paper, we introduce a simple framework, Slimmable Domain Adaptation, to improve cross-domain generalization with a weight-sharing model bank, from which models of different capacities can be sampled to accommodate different accuracy-efficiency trade-offs.
2nd Place Solution for ICCV 2021 VIPriors Image Classification Challenge: An Attract-and-Repulse Learning Approach
Therefore, it is crucial to study how to learn more discriminative representations while avoiding over-fitting.
Transductive CLIP with Class-Conditional Contrastive Learning
This framework can reduce the impact of noisy labels from CLIP model effectively by combining both techniques.
Learning Domain Adaptive Object Detection with Probabilistic Teacher
In addition, we conduct anchor adaptation in parallel with localization adaptation, since anchor can be regarded as a learnable parameter.
Dynamic Domain Generalization
Specifically, we leverage a meta-adjuster to twist the network parameters based on the static model with respect to different data from different domains.
Ranked #26 on
Domain Generalization
on DomainNet
Probing Simile Knowledge from Pre-trained Language Models
In this paper, we probe simile knowledge from PLMs to solve the SI and SG tasks in the unified framework of simile triple completion for the first time.
Semi-Supervised Domain Generalization with Evolving Intermediate Domain
From this perspective, we introduce a novel paradigm of DG, termed as Semi-Supervised Domain Generalization (SSDG), to explore how the labeled and unlabeled source domains can interact, and establish two settings, including the close-set and open-set SSDG.
A Stochastic Composite Augmented Lagrangian Method For Reinforcement Learning
A general theoretical analysis shows that the solutions generated from a sequence of the constrained optimizations converge to the optimal solution of the LP if the error is controlled properly.
Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation
Usually, the given source domain pre-trained model is expected to optimize with only unlabeled target data, which is termed as source-free unsupervised domain adaptation.
Box Re-Ranking: Unsupervised False Positive Suppression for Domain Adaptive Pedestrian Detection
Therefore, it yields our attention to suppress false positive in each target domain in an unsupervised way.
A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data
However, it is difficult to evaluate the quality of pseudo labels since no labels are available in target domain.
DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models
Materials 3, 023804] and is capable of generating uniformly accurate deep learning based PES models in a way that minimizes human intervention and the computational cost for data generation and model training.
Computational Physics
Fast and Robust Rank Aggregation against Model Misspecification
Specifically, the properties of our CoarsenRank are summarized as follows: (1) CoarsenRank is designed for mild model misspecification, which assumes there exist the ideal preferences (consistent with model assumption) that locates in a neighborhood of the actual preferences.
