Search Results for author: Xinyi Yu

Found 29 papers, 7 papers with code

Boosting Box-supervised Instance Segmentation with Pseudo Depth

no code implementations2 Mar 2024 Xinyi Yu, Ling Yan, PengTao Jiang, Hao Chen, Bo Li, Lin Yuanbo Wu, Linlin Ou

This innovative approach empowers the network to simultaneously predict masks and depth, enhancing its ability to capture nuanced depth-related information during the instance segmentation process.

Box-supervised Instance Segmentation Depth Estimation +4

Conformal Predictive Programming for Chance Constrained Optimization

no code implementations12 Feb 2024 Yiqi Zhao, Xinyi Yu, Jyotirmoy V. Deshmukh, Lars Lindemann

Motivated by the advances in conformal prediction (CP), we propose conformal predictive programming (CPP), an approach to solve chance constrained optimization (CCO) problems, i. e., optimization problems with nonlinear constraint functions affected by arbitrary random parameters.

Conformal Prediction LEMMA

Signal Temporal Logic Control Synthesis among Uncontrollable Dynamic Agents with Conformal Prediction

no code implementations7 Dec 2023 Xinyi Yu, Yiqi Zhao, Xiang Yin, Lars Lindemann

We propose a predictive control synthesis framework that guarantees, with high probability, the satisfaction of signal temporal logic (STL) tasks that are defined over the system and uncontrollable stochastic agents.

Conformal Prediction valid

Sleep When Everything Looks Fine: Self-Triggered Monitoring for Signal Temporal Logic Tasks

1 code implementation27 Nov 2023 Chuwei Wang, Xinyi Yu, Jianing Zhao, Lars Lindemann, Xiang Yin

Existing works on online monitoring usually assume that the monitor can acquire system information periodically at each time instant.

Diffusion-based Data Augmentation for Nuclei Image Segmentation

1 code implementation22 Oct 2023 Xinyi Yu, Guanbin Li, Wei Lou, SiQi Liu, Xiang Wan, Yan Chen, Haofeng Li

Therefore, augmenting a dataset with only a few labeled images to improve the segmentation performance is of significant research and application value.

Data Augmentation Image Generation +3

Multi-stream Cell Segmentation with Low-level Cues for Multi-modality Images

1 code implementation22 Oct 2023 Wei Lou, Xinyi Yu, Chenyu Liu, Xiang Wan, Guanbin Li, SiQi Liu, Haofeng Li

Afterward, we train a separate segmentation model for each category using the images in the corresponding category.

Cell Segmentation Segmentation

Safe-by-Construction Autonomous Vehicle Overtaking using Control Barrier Functions and Model Predictive Control

no code implementations10 Oct 2023 Dingran Yuan, Xinyi Yu, ShaoYuan Li, Xiang Yin

In order to tackle the overtaking task in such challenging scenarios, we introduce a novel integrated framework tailored for vehicle overtaking maneuvers.

Autonomous Driving Model Predictive Control

Efficient STL Control Synthesis under Asynchronous Temporal Robustness Constraints

no code implementations24 Jul 2023 Xinyi Yu, Xiang Yin, Lars Lindemann

Given an ATR bound, we compute a sequence of control inputs so that the specification is satisfied by the system as long as each sub-trajectory is shifted not more than the ATR bound.

ShiftNAS: Improving One-shot NAS via Probability Shift

1 code implementation ICCV 2023 Mingyang Zhang, Xinyi Yu, Haodong Zhao, Linlin Ou

To address the problem of uniform sampling, we propose ShiftNAS, a method that can adjust the sampling probability based on the complexity of subnets.

Attribute Neural Architecture Search

Retrieval-Enhanced Visual Prompt Learning for Few-shot Classification

no code implementations4 Jun 2023 Jintao Rong, Hao Chen, Tianxiao Chen, Linlin Ou, Xinyi Yu, Yifan Liu

Prompt learning has become a popular approach for adapting large vision-language models, such as CLIP, to downstream tasks.

Classification Domain Generalization +3

LoRAPrune: Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning

no code implementations28 May 2023 Mingyang Zhang, Hao Chen, Chunhua Shen, Zhen Yang, Linlin Ou, Xinyi Yu, Bohan Zhuang

This is due to their utilization of unstructured pruning on LPMs, impeding the merging of LoRA weights, or their dependence on the gradients of pre-trained weights to guide pruning, which can impose significant memory overhead.

Model Compression Network Pruning

CrossFusion: Interleaving Cross-modal Complementation for Noise-resistant 3D Object Detection

no code implementations19 Apr 2023 Yang Yang, Weijie Ma, Hao Chen, Linlin Ou, Xinyi Yu

The combination of LiDAR and camera modalities is proven to be necessary and typical for 3D object detection according to recent studies.

3D Object Detection Depth Estimation +1

Model Predictive Control for Signal Temporal Logic Specifications with Time Interval Decomposition

1 code implementation15 Nov 2022 Xinyi Yu, Chuwei Wang, Dingran Yuan, ShaoYuan Li, Xiang Yin

However, instead of applying MPC directly for the entire task horizon, we decompose the STL formula into several sub-formulae with disjoint time horizons, and shrinking horizon MPC is applied for each short-horizon sub-formula iteratively.

Computational Efficiency Model Predictive Control

Model Predictive Monitoring of Dynamical Systems for Signal Temporal Logic Specifications

1 code implementation26 Sep 2022 Xinyi Yu, Weijie Dong, Xiang Yin, ShaoYuan Li

To this end, effective approaches for the computation of feasible sets of STL formulae are provided.

MKIoU Loss: Towards Accurate Oriented Object Detection in Aerial Images

no code implementations30 Jun 2022 Jiangping Lu, Xinyi Yu, Mi Lin, Linlin Ou

Thus, the Gaussian Angle Loss (GA Loss) is presented to solve this problem by adding a corrected loss for square targets.

object-detection Object Detection In Aerial Images +2

Multi-subgoal Robot Navigation in Crowds with History Information and Interactions

no code implementations4 May 2022 Xinyi Yu, Jianan Hu, Yuehai Fan, Wancai Zheng, Linlin Ou

Firstly, based on subgraph network, the history information of all agents is aggregated before encoding interactions through a graph neural network, so as to improve the ability of the robot to anticipate the future scenarios implicitly.

Position reinforcement-learning +2

Trinary Tools for Continuously Valued Binary Classifiers

no code implementations18 Apr 2022 Michael Gleicher, Xinyi Yu, YuHeng Chen

Machine learning practitioners must perform model selection, calibration, discretization, performance assessment, tuning, and fairness assessment.

BIG-bench Machine Learning Fairness +1

Online Monitoring of Dynamic Systems for Signal Temporal Logic Specifications with Model Information

no code implementations30 Mar 2022 Xinyi Yu, Weijie Dong, Xiang Yin, ShaoYuan Li

We show that, by explicitly utilizing the model information of the dynamic system, the proposed online monitoring algorithm can falsify or certify of the specification in advance compared with existing algorithms, where no model information is used.

Real-time Rail Recognition Based on 3D Point Clouds

no code implementations8 Jan 2022 Xinyi Yu, Weiqi He, Xuecheng Qian, Yang Yang, Linlin Ou

Accurate rail location is a crucial part in the railway support driving system for safety monitoring.

Conditional Generative Data-free Knowledge Distillation

no code implementations31 Dec 2021 Xinyi Yu, Ling Yan, Yang Yang, Libo Zhou, Linlin Ou

In this paper, we propose a conditional generative data-free knowledge distillation (CGDD) framework for training lightweight networks without any training data.

Conditional Image Generation Data-free Knowledge Distillation +1

Across-Task Neural Architecture Search via Meta Learning

no code implementations12 Oct 2021 Jingtao Rong, Xinyi Yu, Mingyang Zhang, Linlin Ou

In this paper, an across-task neural architecture search (AT-NAS) is proposed to address the problem through combining gradient-based meta-learning with EA-based NAS to learn over the distribution of tasks.

Evolutionary Algorithms Meta-Learning +1

Oriented Object Detection in Aerial Images Based on Area Ratio of Parallelogram

no code implementations21 Sep 2021 Xinyi Yu, Mi Lin, Jiangping Lu, Linlin Ou

Oriented object detection is a challenging task in aerial images since the objects in aerial images are displayed in arbitrary directions and are frequently densely packed.

Object object-detection +2

RepNAS: Searching for Efficient Re-parameterizing Blocks

1 code implementation8 Sep 2021 Mingyang Zhang, Xinyi Yu, Jingtao Rong, Linlin Ou

However, it is still challenging to search for efficient networks due to the gap between the searched constraint and real inference time exists.

Neural Architecture Search

Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization

no code implementations11 Jun 2021 Weichen Chen, Xinyi Yu, Linlin Ou

A specific view-attribute is composed by the extracted attribute feature and four view scores which are predicted by view predictor as the confidences for attribute from different views.

Attribute Pedestrian Attribute Recognition

Effective Model Compression via Stage-wise Pruning

no code implementations10 Nov 2020 Mingyang Zhang, Xinyi Yu, Jingtao Rong, Linlin Ou

To overcome the unfull training, a stage-wise pruning(SWP) method is proposed, which splits a deep supernet into several stage-wise supernets to reduce the candidate number and utilize inplace distillation to supervise the stage training.

Model Compression

Boxer: Interactive Comparison of Classifier Results

no code implementations16 Apr 2020 Michael Gleicher, Aditya Barve, Xinyi Yu, Florian Heimerl

The approach focuses on allowing the user to identify interesting subsets of training and testing instances and comparing performance of the classifiers on these subsets.

Fairness Model Selection

Graph Pruning for Model Compression

no code implementations22 Nov 2019 Mingyang Zhang, Xinyi Yu, Jingtao Rong, Linlin Ou

Different from previous work, we take the node features from a well-trained graph aggregator instead of the hand-craft features, as the states in reinforcement learning.

AutoML Model Compression +2

Cannot find the paper you are looking for? You can Submit a new open access paper.