Search Results for author:
Found 27 papers, 20 papers with code
Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
Model quantization is widely used to compress and accelerate deep neural networks.
SM4Depth: Seamless Monocular Metric Depth Estimation across Multiple Cameras and Scenes by One Model
Firstly, to obtain consistent depth across diverse scenes, we propose a novel metric scale modeling, i. e., variation-based unnormalized depth bins.
An Efficient Learning-based Solver Comparable to Metaheuristics for the Capacitated Arc Routing Problem
Recently, neural networks (NN) have made great strides in combinatorial optimization.
Exploiting Low-level Representations for Ultra-Fast Road Segmentation
The spatial detail branch is firstly designed to extract low-level feature representation for the road by the first stage of ResNet-18.
MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images
We reveal that the abundant normal and abnormal cues implicit in unlabeled test images can be exploited for anomaly determination, which is ignored by prior methods.
Ranked #7 on
Anomaly Detection
on BTAD
Indoor Obstacle Discovery on Reflective Ground via Monocular Camera
Note that obstacle and reflection can be separated by the ground plane in 3D space.
Enhancing the Power of OOD Detection via Sample-Aware Model Selection
In this work we present a novel perspective on detecting out-of-distribution (OOD) samples and propose an algorithm for sample-aware model selection to enhance the effectiveness of OOD detection.
FDINet: Protecting against DNN Model Extraction via Feature Distortion Index
FDINET exhibits the capability to identify colluding adversaries with an accuracy exceeding 91%.
Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects
The recently proposed open-world object and open-set detection have achieved a breakthrough in finding never-seen-before objects and distinguishing them from known ones.
Ranked #1 on
Open World Object Detection
on COCO-OOD
LipFormer: Learning to Lipread Unseen Speakers based on Visual-Landmark Transformers
However, generalizing these methods to unseen speakers incurs catastrophic performance degradation due to the limited number of speakers in training bank and the evident visual variations caused by the shape/color of lips for different speakers.
Boosting Out-of-Distribution Detection with Multiple Pre-trained Models
This advance raises a natural question: Can we leverage the diversity of multiple pre-trained models to improve the performance of post hoc detection methods?
MEGCF: Multimodal Entity Graph Collaborative Filtering for Personalized Recommendation
This paper aims at solving the mismatch problem between MFE and UIM, so as to generate high-quality embedding representations and better model multimodal user preferences.
Joint Multi-grained Popularity-aware Graph Convolution Collaborative Filtering for Recommendation
In this work, we propose to model multi-grained popularity features and jointly learn them together with high-order connectivity, to match the differentiation of user preferences exhibited in popularity features.
Multivariate Time Series Anomaly Detection with Few Positive Samples
This practical situation calls for methodologies to leverage these small number of anomaly events to create a better anomaly detector.
MAD: Self-Supervised Masked Anomaly Detection Task for Multivariate Time Series
Our experimental results demonstrate that MAD can achieve better anomaly detection rates over traditional NSP approaches when using exactly the same neural network (NN) base models, and can be modified to run as fast as NSP models during test time on the same hardware, thus making it an ideal upgrade for many existing NSP-based NN anomaly detection models.
MARF: Multiscale Adaptive-switch Random Forest for Leg Detection with 2D Laser Scanners
Moreover, we further apply the proposed MARF to the people detection and tracking system, achieving a considerable gain in all metrics.
Fast Road Segmentation via Uncertainty-aware Symmetric Network
The high performance of RGB-D based road segmentation methods contrasts with their rare application in commercial autonomous driving, which is owing to two reasons: 1) the prior methods cannot achieve high inference speed and high accuracy in both ways; 2) the different properties of RGB and depth data are not well-exploited, limiting the reliability of predicted road.
Monocular Depth Distribution Alignment with Low Computation
In this paper, we model the majority of accuracy contrast between them as the difference of depth distribution, which we call "Distribution drift".
Tiny Obstacle Discovery by Occlusion-Aware Multilayer Regression
Edges are the fundamental visual element for discovering tiny obstacles using a monocular camera.
Noise Doesn't Lie: Towards Universal Detection of Deep Inpainting
A promising countermeasure against such forgeries is deep inpainting detection, which aims to locate the inpainted regions in an image.
Boundary-induced and scene-aggregated network for monocular depth prediction
However, two issues remain unresolved: (1) The deep feature encodes the wrong farthest region in a scene, which leads to a distorted 3D structure of the predicted depth; (2) The low-level features are insufficient utilized, which makes it even harder to estimate the depth near the edge with sudden depth change.
RGCF: Refined Graph Convolution Collaborative Filtering with concise and expressive embedding
In this work, we develop a new GCN-based Collaborative Filtering model, named Refined Graph convolution Collaborative Filtering(RGCF), where the construction of the embeddings of users (items) are delicately redesigned from several aspects during the aggregation on the graph.
Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving Applications
Our contributions are twofold: a) a novel dense connected prediction (DCP) layer is proposed to provide better object-level depth estimation and b) specifically for autonomous driving scenarios, dense geometrical constrains (DGC) is introduced so that precise scale factor can be recovered without additional cost for autonomous vehicles.
Ranked #59 on
Monocular Depth Estimation
on KITTI Eigen split
Occlusion-shared and Feature-separated Network for Occlusion Relationship Reasoning
On one hand, considering the relevance between edge and orientation, two sub-networks are designed to share the occlusion cue.
A Novel Multi-layer Framework for Tiny Obstacle Discovery
For tiny obstacle discovery in a monocular image, edge is a fundamental visual element.
Deep Item-based Collaborative Filtering for Top-N Recommendation
In this work, we propose a more expressive ICF solution by accounting for the nonlinear and higher-order relationship among items.
A New Medical Diagnosis Method Based on Z-Numbers
In this paper, a new decision making methodology based on Z-numbers is presented.
