Search Results for author:
Found 36 papers, 19 papers with code
OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks
Compared with other computer vision tasks, it is rather difficult to collect a large-scale MVS dataset as it requires expensive active scanners and labor-intensive process to obtain ground truth 3D structures.
Visibility-aware Multi-view Stereo Network
As such, the adverse influence of occluded pixels is suppressed in the cost fusion.
Ranked #1 on
Point Clouds
on DTU
Learning Signed Distance Field for Multi-view Surface Reconstruction
In this work, we introduce a novel neural surface reconstruction framework that leverages the knowledge of stereo matching and feature consistency to optimize the implicit surface representation.
MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning
To solve these problems, we propose a novel deep learning-based interactive segmentation method that not only has high efficiency due to only requiring clicks as user inputs but also generalizes well to a range of previously unseen objects.
3DSAM-adapter: Holistic Adaptation of SAM from 2D to 3D for Promptable Medical Image Segmentation
Notably, the original SAM architecture is designed for 2D natural images, therefore would not be able to extract the 3D spatial information from volumetric medical data effectively.
NeILF: Neural Incident Light Field for Physically-based Material Estimation
We present a differentiable rendering framework for material and lighting estimation from multi-view images and a reconstructed geometry.
Contrastive Semi-supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures
To solve this problem, we propose Contrastive Semi-supervised learning for Cross Anatomy Domain Adaptation (CS-CADA) that adapts a model to segment similar structures in a target domain, which requires only limited annotations in the target domain by leveraging a set of existing annotated images of similar structures in a source domain.
CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image Segmentation
First, a disentangle network is proposed to decompose an image into a domain-invariant anatomical representation and a domain-specific style code, where the former is sent to a segmentation model that is not affected by the domain shift, and the disentangle network is regularized by a decoder that combines the anatomical and style codes to reconstruct the input image.
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
The process is hard, often requires models with large capacity, and suffers from significant loss on clean data accuracy.
Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Models
This paper introduces a novel and significant challenge for Vision Language Models (VLMs), termed Unsolvable Problem Detection (UPD).
Contrastive Domain Disentanglement for Generalizable Medical Image Segmentation
To tackle this deficiency, we propose Contrastive Domain Disentangle (CDD) network for generalizable medical image segmentation.
Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments
We then propose Mixture Outlier Exposure (MixOE), which mixes ID data and training outliers to expand the coverage of different OOD granularities, and trains the model such that the prediction confidence linearly decays as the input transitions from ID to OOD.
Medical Image Classification
Out-of-Distribution Detection
+1
Learning Stereo Matchability in Disparity Regression Networks
Finally, a matchability-aware disparity refinement is introduced to improve the depth inference in weakly matchable regions.
Ranked #2 on
Stereo Disparity Estimation
on KITTI 2015
Exploring Bit-Slice Sparsity in Deep Neural Networks for Efficient ReRAM-Based Deployment
However, the power hungry analog-to-digital converters (ADCs) prevent the practical deployment of ReRAM-based DNN accelerators on end devices with limited chip area and power budget.
Privacy Leakage of Adversarial Training Models in Federated Learning Systems
Adversarial Training (AT) is crucial for obtaining deep neural networks that are robust to adversarial attacks, yet recent works found that it could also make models more vulnerable to privacy attacks.
Domain Composition and Attention for Unseen-Domain Generalizable Medical Image Segmentation
First, we present a domain composition method that represents one certain domain by a linear combination of a set of basis representations (i. e., a representation bank).
SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection
Building up reliable Out-of-Distribution (OOD) detectors is challenging, often requiring the use of OOD data during training.
SD-NAE: Generating Natural Adversarial Examples with Stable Diffusion
Natural Adversarial Examples (NAEs), images arising naturally from the environment and capable of deceiving classifiers, are instrumental in robustly evaluating and identifying vulnerabilities in trained models.
A novel active learning framework for classification: using weighted rank aggregation to achieve multiple query criteria
The proposed method serves as a heuristic means to select high-value samples of high scalability and generality and is implemented through a three-step process: (1) the transformation of the sample selection to sample ranking and scoring, (2) the computation of the self-adaptive weights of each criterion, and (3) the weighted aggregation of each sample rank list.
Towards Leveraging the Information of Gradients in Optimization-based Adversarial Attack
We intuitively and empirically prove the rationality of our method in reducing the search space.
Weakly Supervised Vessel Segmentation in X-ray Angiograms by Self-Paced Learning from Noisy Labels with Suggestive Annotation
The segmentation of coronary arteries in X-ray angiograms by convolutional neural networks (CNNs) is promising yet limited by the requirement of precisely annotating all pixels in a large number of training images, which is extremely labor-intensive especially for complex coronary trees.
Can Targeted Adversarial Examples Transfer When the Source and Target Models Have No Label Space Overlap?
During the online phase of the attack, we then leverage representations of highly related proxy classes from the whitebox distribution to fool the blackbox model into predicting the desired target class.
SS-CADA: A Semi-Supervised Cross-Anatomy Domain Adaptation for Coronary Artery Segmentation
To solve this problem, we propose a Semi-Supervised Cross-Anatomy Domain Adaptation (SS-CADA) which requires only limited annotations for coronary arteries in XAs.
Critical Regularizations for Neural Surface Reconstruction in the Wild
The first one is the Hessian regularization that smoothly diffuses the signed distance values to the entire distance field given noisy and incomplete input.
Learning towards Synchronous Network Memorizability and Generalizability for Continual Segmentation across Multiple Sites
In clinical practice, a segmentation network is often required to continually learn on a sequential data stream from multiple sites rather than a consolidated set, due to the storage cost and privacy restriction.
Fine-grain Inference on Out-of-Distribution Data with Hierarchical Classification
Furthermore, we diagnose the classifiers performance at each level of the hierarchy improving the explainability and interpretability of the models predictions.
Deep learning reveals the common spectrum underlying multiple brain disorders in youth and elders from brain functional networks
Brain disorders in the early and late life of humans potentially share pathological alterations in brain functions.
Structure-aware registration network for liver DCE-CT images
In addition, such paired organ segmentations are not always available in DCE-CT images due to the flow of contrast agents.
NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimation
We present a novel differentiable rendering framework for joint geometry, material, and lighting estimation from multi-view images.
Construction of unbiased dental template and parametric dental model for precision digital dentistry
In this study, we develop an unbiased dental template by constructing an accurate dental atlas from CBCT images with guidance of teeth segmentation.
JointNet: Extending Text-to-Image Diffusion for Dense Distribution Modeling
We introduce JointNet, a novel neural network architecture for modeling the joint distribution of images and an additional dense modality (e. g., depth maps).
Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion
The multi-view 2. 5D diffusion directly models the structural distribution of 3D data, while still maintaining the strong generalization ability of the original 2D diffusion model, filling the gap between 2D diffusion-based and direct 3D diffusion-based methods for 3D content generation.
S^2Former-OR: Single-Stage Bimodal Transformer for Scene Graph Generation in OR
In this study, we introduce a novel single-stage bimodal transformer framework for SGG in the OR, termed S^2Former-OR, aimed to complementally leverage multi-view 2D scenes and 3D point clouds for SGG in an end-to-end manner.
Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models
The problem of pre-training data detection for large language models (LLMs) has received growing attention due to its implications in critical issues like copyright violation and test data contamination.
OSR-ViT: A Simple and Modular Framework for Open-Set Object Detection and Discovery
Our method also excels in low-data settings, outperforming supervised baselines using a fraction of the training data.
