Search Results for author: Jiaming Zhang

Found 85 papers, 61 papers with code

Deformable Mamba for Wide Field of View Segmentation

1 code implementation25 Nov 2024 Jie Hu, Junwei Zheng, Jiale Wei, Jiaming Zhang, Rainer Stiefelhagen

Wide-FoV cameras, like fisheye and panoramic setups, are essential for broader perception but introduce significant distortions in 180{\deg} and 360{\deg} images, complicating dense prediction tasks.

Decoder Mamba +2

Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems

1 code implementation21 Nov 2024 Qihao Yuan, Jiaming Zhang, Kailai Li, Rainer Stiefelhagen

3D visual grounding (3DVG) aims to locate objects in a 3D scene with natural language descriptions.

3D visual grounding Negation

TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models

no code implementations20 Nov 2024 Xin Wang, Kai Chen, Jiaming Zhang, Jingjing Chen, Xingjun Ma

TAPT is a test-time defense method that learns defensive bimodal (textual and visual) prompts to robustify the inference process of CLIP.

Adversarial Robustness

Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models

1 code implementation25 Oct 2024 Yige Li, Hanxun Huang, Jiaming Zhang, Xingjun Ma, Yu-Gang Jiang

Specifically, EBYD first exposes the backdoor functionality in the backdoored model through a model preprocessing step called backdoor exposure, and then applies detection and removal methods to the exposed model to identify and eliminate the backdoor features.

backdoor defense Model Editing +1

Debiasing Vison-Language Models with Text-Only Training

no code implementations12 Oct 2024 Yunfan Yang, Chaoquan Jiang, Zhiyu Lin, Jinlin Xiao, Jiaming Zhang, Jitao Sang

Existing debiasing methods struggle to obtain sufficient image samples for minority groups and incur high costs for group labeling.

Large Language Model

AnyAttack: Targeted Adversarial Attacks on Vision-Language Models toward Any Images

no code implementations7 Oct 2024 Jiaming Zhang, Junhong Ye, Xingjun Ma, Yige Li, Yunfan Yang, Jitao Sang, Dit-yan Yeung

In this paper, we propose AnyAttack, a self-supervised framework that generates targeted adversarial images for VLMs without label supervision, allowing any image to serve as a target for the attack.

Image Captioning Image-text Retrieval +1

@Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology

no code implementations21 Sep 2024 Xin Jiang, Junwei Zheng, Ruiping Liu, Jiahang Li, Jiaming Zhang, Sven Matthiesen, Rainer Stiefelhagen

As Vision-Language Models (VLMs) advance, human-centered Assistive Technologies (ATs) for helping People with Visual Impairments (PVIs) are evolving into generalists, capable of performing multiple tasks simultaneously.

Benchmarking Depth Estimation +6

OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic Mapping

1 code implementation20 Sep 2024 Jiale Wei, Junwei Zheng, Ruiping Liu, Jie Hu, Jiaming Zhang, Rainer Stiefelhagen

This work advances BEV semantic mapping in autonomous driving, paving the way for more advanced and reliable autonomous systems.

Autonomous Driving Mamba

CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence

1 code implementation26 Aug 2024 Chaochao Chen, Jiaming Zhang, Yizhao Zhang, Li Zhang, Lingjuan Lyu, Yuyuan Li, Biao Gong, Chenggang Yan

Specifically, we consider the deeper influence of unlearning on recommendation fairness and robustness towards data with varying impact levels.

Fairness Machine Unlearning +1

Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compression

1 code implementation6 Aug 2024 Jonas Schmitt, Ruiping Liu, Junwei Zheng, Jiaming Zhang, Rainer Stiefelhagen

Extensive experiments demonstrate the generalizability of our framework, encompassing both convolutional neural network (CNN) and transformer models, as well as image classification and segmentation tasks.

Image Classification Knowledge Distillation +2

Long Range Switching Time Series Prediction via State Space Model

no code implementations27 Jul 2024 Jiaming Zhang, Yang Ding, Yunfeng Gao

In this study, we delve into the Structured State Space Model (S4), Change Point Detection methodologies, and the Switching Non-linear Dynamics System (SNLDS).

Change Point Detection Time Series +1

Rethinking Attention Module Design for Point Cloud Analysis

no code implementations27 Jul 2024 Chengzhi Wu, Kaige Wang, Zeyun Zhong, Hao Fu, Junwei Zheng, Jiaming Zhang, Julius Pfrommer, Jürgen Beyerer

In recent years, there have been significant advancements in applying attention mechanisms to point cloud analysis.

Point Cloud Classification

Referring Atomic Video Action Recognition

1 code implementation2 Jul 2024 Kunyu Peng, Jia Fu, Kailun Yang, Di Wen, Yufan Chen, Ruiping Liu, Junwei Zheng, Jiaming Zhang, M. Saquib Sarfraz, Rainer Stiefelhagen, Alina Roitberg

Since these existing methods underperform on RAVAR, we introduce RefAtomNet -- a novel cross-stream attention-driven method specialized for the unique challenges of RAVAR: the need to interpret a textual referring expression for the targeted individual, utilize this reference to guide the spatial localization and harvest the prediction of the atomic actions for the referring person.

Action Recognition Question Answering +4

Occlusion-Aware Seamless Segmentation

1 code implementation2 Jul 2024 Yihong Cao, Jiaming Zhang, Hao Shi, Kunyu Peng, Yuhongxuan Zhang, HUI ZHANG, Rainer Stiefelhagen, Kailun Yang

Our method achieves state-of-the-art performance on the BlendPASS dataset, reaching a remarkable mAPQ of 26. 58% and mIoU of 43. 66%.

Benchmarking Domain Adaptation +2

Open Panoramic Segmentation

1 code implementation2 Jul 2024 Junwei Zheng, Ruiping Liu, Yufan Chen, Kunyu Peng, Chengzhi Wu, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen

To tackle this problem, in this work, we define a new task termed Open Panoramic Segmentation (OPS), where models are trained with FoV-restricted pinhole images in the source domain in an open-vocabulary setting while evaluated with FoV-open panoramic images in the target domain, enabling the zero-shot open panoramic semantic segmentation ability of models.

Open-Vocabulary Panoramic Semantic Segmentation

AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks

no code implementations22 May 2024 Omar Moured, Jiaming Zhang, M. Saquib Sarfraz, Rainer Stiefelhagen

Chart summarization is a crucial task for blind and visually impaired individuals as it is their primary means of accessing and interpreting graphical data.

DTCLMapper: Dual Temporal Consistent Learning for Vectorized HD Map Construction

1 code implementation9 May 2024 Siyu Li, Jiacheng Lin, Hao Shi, Jiaming Zhang, Song Wang, You Yao, Zhiyong Li, Kailun Yang

In this paper, we revisit the temporal fusion of vectorized HD maps, focusing on temporal instance consistency and temporal map consistency learning.

Contrastive Learning Scene Understanding +1

Segment Any Medical Model Extended

1 code implementation26 Mar 2024 Yihao Liu, Jiaming Zhang, Andres Diaz-Pinto, Haowei Li, Alejandro Martin-Gomez, Amir Kheradmand, Mehran Armand

To this end, a unified platform helps push the boundary of the foundation model for medical images, facilitating the use, modification, and validation of SAM and its variants in medical image segmentation.

Data Augmentation Image Segmentation +4

Realtime Robust Shape Estimation of Deformable Linear Object

no code implementations24 Mar 2024 Jiaming Zhang, Zhaomeng Zhang, Yihao Liu, Yaqian Chen, Amir Kheradmand, Mehran Armand

We propose a robust method to estimate the shape of linear deformable objects in realtime using scattered and unordered key points.

Object Unity

RoDLA: Benchmarking the Robustness of Document Layout Analysis Models

1 code implementation CVPR 2024 Yufan Chen, Jiaming Zhang, Kunyu Peng, Junwei Zheng, Ruiping Liu, Philip Torr, Rainer Stiefelhagen

To address this, we are the first to introduce a robustness benchmark for DLA models, which includes 450K document images of three datasets.

Benchmarking Document Layout Analysis

Skeleton-Based Human Action Recognition with Noisy Labels

1 code implementation15 Mar 2024 Yi Xu, Kunyu Peng, Di Wen, Ruiping Liu, Junwei Zheng, Yufan Chen, Jiaming Zhang, Alina Roitberg, Kailun Yang, Rainer Stiefelhagen

In this study, we bridge this gap by implementing a framework that augments well-established skeleton-based human action recognition methods with label-denoising strategies from various research areas to serve as the initial benchmark.

Action Recognition Denoising +3

Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving

1 code implementation13 Mar 2024 Hao Shi, Song Wang, Jiaming Zhang, Xiaoting Yin, Zhongdao Wang, Guangming Wang, Jianke Zhu, Kailun Yang, Kaiwei Wang

Vision-based occupancy prediction, also known as 3D Semantic Scene Completion (SSC), presents a significant challenge in computer vision.

3D Semantic Scene Completion Autonomous Driving

Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation

1 code implementation30 Jan 2024 Ruiping Liu, Jiaming Zhang, Kunyu Peng, Yufan Chen, Ke Cao, Junwei Zheng, M. Saquib Sarfraz, Kailun Yang, Rainer Stiefelhagen

Integrating information from multiple modalities enhances the robustness of scene perception systems in autonomous vehicles, providing a more comprehensive and reliable sensory framework.

Autonomous Vehicles Scene Segmentation

Navigating Open Set Scenarios for Skeleton-based Action Recognition

1 code implementation11 Dec 2023 Kunyu Peng, Cheng Yin, Junwei Zheng, Ruiping Liu, David Schneider, Jiaming Zhang, Kailun Yang, M. Saquib Sarfraz, Rainer Stiefelhagen, Alina Roitberg

In real-world scenarios, human actions often fall outside the distribution of training data, making it crucial for models to recognize known actions and reject unknown ones.

cross-modal alignment Novelty Detection +4

Adversarial Prompt Tuning for Vision-Language Models

1 code implementation19 Nov 2023 Jiaming Zhang, Xingjun Ma, Xin Wang, Lingyu Qiu, Jiaqi Wang, Yu-Gang Jiang, Jitao Sang

With the rapid advancement of multimodal learning, pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capacities in bridging the gap between visual and language modalities.

Adversarial Robustness

CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementarity

1 code implementation4 Oct 2023 Hao Shi, Chengshan Pang, Jiaming Zhang, Kailun Yang, Yuhao Wu, Huajian Ni, Yining Lin, Rainer Stiefelhagen, Kaiwei Wang

Roadside camera-driven 3D object detection is a crucial task in intelligent transportation systems, which extends the perception range beyond the limitations of vision-centric vehicles and enhances road safety.

feature selection Monocular 3D Object Detection +1

Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision

1 code implementation21 Sep 2023 Yiping Wei, Kunyu Peng, Alina Roitberg, Jiaming Zhang, Junwei Zheng, Ruiping Liu, Yufan Chen, Kailun Yang, Rainer Stiefelhagen

These works overlooked the differences in performance among modalities, which led to the propagation of erroneous knowledge between modalities while only three fundamental modalities, i. e., joints, bones, and motions are used, hence no additional modalities are explored.

Action Recognition Knowledge Distillation +3

Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation

no code implementations25 Aug 2023 Jiaming Zhang, Yutao Cui, Gangshan Wu, LiMin Wang

To overcome these issues, we propose a unified VOS framework, coined as JointFormer, for joint modeling the three elements of feature, correspondence, and a compressed memory.

Semantic Segmentation Video Object Segmentation +1

OAFuser: Towards Omni-Aperture Fusion for Light Field Semantic Segmentation

2 code implementations28 Jul 2023 Fei Teng, Jiaming Zhang, Kunyu Peng, Yaonan Wang, Rainer Stiefelhagen, Kailun Yang

To simultaneously streamline the redundant information from the light field cameras and avoid feature loss during network propagation, we present a simple yet very effective Sub-Aperture Fusion Module (SAFM).

Autonomous Driving Scene Understanding +1

Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments

1 code implementation15 Jul 2023 Ruiping Liu, Jiaming Zhang, Kunyu Peng, Junwei Zheng, Ke Cao, Yufan Chen, Kailun Yang, Rainer Stiefelhagen

Grounded Situation Recognition (GSR) is capable of recognizing and interpreting visual scenes in a contextually intuitive way, yielding salient activities (verbs) and the involved entities (roles) depicted in images.

Decoder Grounded Situation Recognition +2

Tightly-Coupled LiDAR-Visual SLAM Based on Geometric Features for Mobile Agents

no code implementations15 Jul 2023 Ke Cao, Ruiping Liu, Ze Wang, Kunyu Peng, Jiaming Zhang, Junwei Zheng, Zhifeng Teng, Kailun Yang, Rainer Stiefelhagen

On the other hand, the entire line segment detected by the visual subsystem overcomes the limitation of the LiDAR subsystem, which can only perform the local calculation for geometric features.

Autonomous Navigation Pose Estimation +2

Introducing Foundation Models as Surrogate Models: Advancing Towards More Practical Adversarial Attacks

no code implementations13 Jul 2023 Jiaming Zhang, Jitao Sang, Qi Yi, Changsheng Xu

Harnessing the concept of non-robust features, we elaborate on two guiding principles for surrogate model selection to explain why the foundational model is an optimal choice for this role.

Adversarial Attack Attribute +1

Federated Unlearning via Active Forgetting

no code implementations7 Jul 2023 Yuyuan Li, Chaochao Chen, Xiaolin Zheng, Jiaming Zhang

To this end, we propose a novel federated unlearning framework based on incremental learning, which is independent of specific models and federated settings.

Federated Learning Incremental Learning +1

Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains

2 code implementations15 May 2023 Kunyu Peng, Di Wen, David Schneider, Jiaming Zhang, Kailun Yang, M. Saquib Sarfraz, Rainer Stiefelhagen, Alina Roitberg

In this work, we focus on Few-Shot Domain Adaptation for Activity Recognition (FSDA-AR), which leverages a very small amount of labeled target videos to achieve effective adaptation.

Action Recognition Unsupervised Domain Adaptation

Bi-Mapper: Holistic BEV Semantic Mapping for Autonomous Driving

1 code implementation7 May 2023 Siyu Li, Kailun Yang, Hao Shi, Jiaming Zhang, Jiacheng Lin, Zhifeng Teng, Zhiyong Li

At the same time, an Across-Space Loss (ASL) is designed to mitigate the negative impact of geometric distortions.

Autonomous Driving

SAMM (Segment Any Medical Model): A 3D Slicer Integration to SAM

1 code implementation12 Apr 2023 Yihao Liu, Jiaming Zhang, Zhangcong She, Amir Kheradmand, Mehran Armand

To assist with the development, assessment, and application of SAM on medical images, we introduce Segment Any Medical Model (SAMM), an extension of SAM on 3D Slicer - an image processing and visualization software extensively used by the medical imaging community.

Image Segmentation Segmentation +1

FishDreamer: Towards Fisheye Semantic Completion via Unified Image Outpainting and Segmentation

1 code implementation24 Mar 2023 Hao Shi, Yu Li, Kailun Yang, Jiaming Zhang, Kunyu Peng, Alina Roitberg, Yaozu Ye, Huajian Ni, Kaiwei Wang, Rainer Stiefelhagen

This paper raises the new task of Fisheye Semantic Completion (FSC), where dense texture, structure, and semantics of a fisheye image are inferred even beyond the sensor field-of-view (FoV).

Image Outpainting Semantic Segmentation

Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples

1 code implementation CVPR 2023 Jiaming Zhang, Xingjun Ma, Qi Yi, Jitao Sang, Yu-Gang Jiang, YaoWei Wang, Changsheng Xu

Furthermore, we propose to leverage VisionandLanguage Pre-trained Models (VLPMs) like CLIP as the surrogate model to improve the transferability of the crafted UCs to diverse domains.

Data Poisoning

Computational Imaging for Machine Perception: Transferring Semantic Segmentation beyond Aberrations

1 code implementation21 Nov 2022 Qi Jiang, Hao Shi, Shaohua Gao, Jiaming Zhang, Kailun Yang, Lei Sun, Huajian Ni, Kaiwei Wang

Further, we propose Computational Imaging Assisted Domain Adaptation (CIADA) to leverage prior knowledge of CI for robust performance in SSOA.

Scene Understanding Semantic Segmentation +1

Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation

1 code implementation25 Jul 2022 Jiaming Zhang, Kailun Yang, Hao Shi, Simon Reiß, Kunyu Peng, Chaoxiang Ma, Haodong Fu, Philip H. S. Torr, Kaiwei Wang, Rainer Stiefelhagen

In this paper, we address panoramic semantic segmentation which is under-explored due to two critical challenges: (1) image distortions and object deformations on panoramas; (2) lack of semantic annotations in the 360{\deg} imagery.

Pseudo Label Segmentation +2

Trans4Map: Revisiting Holistic Bird's-Eye-View Mapping from Egocentric Images to Allocentric Semantics with Vision Transformers

1 code implementation13 Jul 2022 Chang Chen, Jiaming Zhang, Kailun Yang, Kunyu Peng, Rainer Stiefelhagen

Humans have an innate ability to sense their surroundings, as they can extract the spatial representation from the egocentric perception and form an allocentric semantic map via spatial transformation and memory updating.

Decoder Semantic Segmentation

Multi-modal Depression Estimation based on Sub-attentional Fusion

1 code implementation13 Jul 2022 Ping-Cheng Wei, Kunyu Peng, Alina Roitberg, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen

Failure to timely diagnose and effectively treat depression leads to over 280 million people suffering from this psychological disorder worldwide.

Towards Adversarial Attack on Vision-Language Pre-training Models

1 code implementation19 Jun 2022 Jiaming Zhang, Qi Yi, Jitao Sang

While vision-language pre-training model (VLP) has shown revolutionary improvements on various vision-language (V+L) tasks, the studies regarding its adversarial robustness remain largely unexplored.

Adversarial Attack Adversarial Robustness

Low-Mid Adversarial Perturbation against Unauthorized Face Recognition System

no code implementations19 Jun 2022 Jiaming Zhang, Qi Yi, Dongyuan Lu, Jitao Sang

In light of the growing concerns regarding the unauthorized use of facial recognition systems and its implications on individual privacy, the exploration of adversarial perturbations as a potential countermeasure has gained traction.

Face Recognition

MatchFormer: Interleaving Attention in Transformers for Feature Matching

1 code implementation17 Mar 2022 Qing Wang, Jiaming Zhang, Kailun Yang, Kunyu Peng, Rainer Stiefelhagen

While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-based methods with a sequential extract-to-match pipeline, fail to make use of the matching capacity of the encoder and tend to overburden the decoder for matching.

Decoder Homography Estimation +2

TransDARC: Transformer-based Driver Activity Recognition with Latent Space Feature Calibration

1 code implementation2 Mar 2022 Kunyu Peng, Alina Roitberg, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen

This module operates in the latent feature-space enriching and diversifying the training set at feature-level in order to improve generalization to novel data appearances, (e. g., sensor changes) and general feature quality.

Human Activity Recognition

Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation

1 code implementation CVPR 2022 Jiaming Zhang, Kailun Yang, Chaoxiang Ma, Simon Reiß, Kunyu Peng, Rainer Stiefelhagen

To get around this domain difference and bring together semantic annotations from pinhole- and 360-degree surround-visuals, we propose to learn object deformations and panoramic image distortions in the Deformable Patch Embedding (DPE) and Deformable MLP (DMLP) components which blend into our Transformer for PAnoramic Semantic Segmentation (Trans4PASS) model.

Scene Understanding Semantic Segmentation +1

TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation

2 code implementations27 Feb 2022 Ruiping Liu, Kailun Yang, Alina Roitberg, Jiaming Zhang, Kunyu Peng, Huayao Liu, Yaonan Wang, Rainer Stiefelhagen

Furthermore, we introduce two optimization modules to enhance the patch embedding distillation from different perspectives: (1) Global-Local Context Mixer (GL-Mixer) extracts both global and local information of a representative embedding; (2) Embedding Assistant (EA) acts as an embedding method to seamlessly bridge teacher and student models with the teacher's number of channels.

Autonomous Driving Knowledge Distillation +3

Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions

2 code implementations23 Feb 2022 Kunyu Peng, Alina Roitberg, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen

Yet, the research of data-scarce recognition from skeleton sequences, such as one-shot action recognition, does not explicitly consider occlusions despite their everyday pervasiveness.

Action Classification Action Recognition +2

Should I take a walk? Estimating Energy Expenditure from Video Data

1 code implementation1 Feb 2022 Kunyu Peng, Alina Roitberg, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen

To study this underresearched task, we introduce Vid2Burn -- an omni-source benchmark for estimating caloric expenditure from video data featuring both, high- and low-intensity activities for which we derive energy expenditure annotations based on models established in medical literature.

Video Recognition

Exploring Event-driven Dynamic Context for Accident Scene Segmentation

1 code implementation9 Dec 2021 Jiaming Zhang, Kailun Yang, Rainer Stiefelhagen

Moreover, in order to evaluate the segmentation performance in traffic accidents, we provide a pixel-wise annotated accident dataset, namely DADA-seg, which contains a variety of critical scenarios from traffic accidents.

Ranked #3 on Semantic Segmentation on DADA-seg (using extra training data)

Scene Segmentation Segmentation

Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation

1 code implementation21 Oct 2021 Jiaming Zhang, Chaoxiang Ma, Kailun Yang, Alina Roitberg, Kunyu Peng, Rainer Stiefelhagen

We look at this problem from the perspective of domain adaptation and bring panoramic semantic segmentation to a setting, where labelled training data originates from a different distribution of conventional pinhole camera images.

Ranked #7 on Semantic Segmentation on DensePASS (using extra training data)

Autonomous Vehicles Segmentation +2

Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance

1 code implementation20 Aug 2021 Jiaming Zhang, Kailun Yang, Angela Constantinescu, Kunyu Peng, Karin Müller, Rainer Stiefelhagen

In this paper, we build a wearable system with a novel dual-head Transformer for Transparency (Trans4Trans) perception model, which can segment general- and transparent objects.

Ranked #2 on Semantic Segmentation on DADA-seg (using extra training data)

Decoder Navigate +2

DensePASS: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation with Attention-Augmented Context Exchange

1 code implementation13 Aug 2021 Chaoxiang Ma, Jiaming Zhang, Kailun Yang, Alina Roitberg, Rainer Stiefelhagen

First, we formalize the task of unsupervised domain adaptation for panoramic semantic segmentation, where a network trained on labelled examples from the source domain of pinhole camera data is deployed in a different target domain of panoramic images, for which no labels are available.

Segmentation Semantic Segmentation +1

Benign Adversarial Attack: Tricking Models for Goodness

no code implementations26 Jul 2021 Jitao Sang, Xian Zhao, Jiaming Zhang, Zhiyu Lin

In spite of the successful application in many fields, machine learning models today suffer from notorious problems like vulnerability to adversarial examples.

Adversarial Attack Attribute +2

A Modulation Layer to Increase Neural Network Robustness Against Data Quality Issues

1 code implementation19 Jul 2021 Mohamed Abdelhack, Jiaming Zhang, Sandhya Tripathi, Bradley A Fritz, Daniel Felsky, Michael S Avidan, Yixin Chen, Christopher R King

Data missingness and quality are common problems in machine learning, especially for high-stakes applications such as healthcare.

Imputation

Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World

1 code implementation7 Jul 2021 Jiaming Zhang, Kailun Yang, Angela Constantinescu, Kunyu Peng, Karin Müller, Rainer Stiefelhagen

Common fully glazed facades and transparent objects present architectural barriers and impede the mobility of people with low vision or blindness, for instance, a path detected behind a glass door is inaccessible unless it is correctly perceived and reacted.

Decoder Navigate +2

MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding

1 code implementation1 Jul 2021 Kunyu Peng, Juncong Fei, Kailun Yang, Alina Roitberg, Jiaming Zhang, Frank Bieder, Philipp Heidenreich, Christoph Stiller, Rainer Stiefelhagen

At the heart of all automated driving systems is the ability to sense the surroundings, e. g., through semantic segmentation of LiDAR sequences, which experienced a remarkable progress due to the release of large datasets such as SemanticKITTI and nuScenes-LidarSeg.

3D Object Detection Graph Attention +4

Pose2Drone: A Skeleton-Pose-based Framework for Human-Drone Interaction

1 code implementation27 May 2021 Zdravko Marinov, Stanka Vasileva, Qing Wang, Constantin Seibold, Jiaming Zhang, Rainer Stiefelhagen

Our framework provides the functionality to control the movement of the drone with simple arm gestures and to follow the user while keeping a safe distance.

Pose Estimation

Capturing Omni-Range Context for Omnidirectional Segmentation

1 code implementation CVPR 2021 Kailun Yang, Jiaming Zhang, Simon Reiß, Xinxin Hu, Rainer Stiefelhagen

Convolutional Networks (ConvNets) excel at semantic segmentation and have become a vital component for perception in autonomous driving.

Ranked #10 on Semantic Segmentation on DensePASS (using extra training data)

Autonomous Driving Image Segmentation +2

Perception Framework through Real-Time Semantic Segmentation and Scene Recognition on a Wearable System for the Visually Impaired

no code implementations6 Mar 2021 Yingzhi Zhang, Haoye Chen, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen

As the scene information, including objectness and scene type, are important for people with visual impairment, in this work we present a multi-task efficient perception system for the scene parsing and recognition tasks.

Real-Time Semantic Segmentation Scene Recognition

A Novel Application of Image-to-Image Translation: Chromosome Straightening Framework by Learning from a Single Image

no code implementations4 Mar 2021 Sifan Song, Daiyun Huang, Yalun Hu, Chunxiao Yang, Jia Meng, Fei Ma, Frans Coenen, Jiaming Zhang, Jionglong Su

To address the flaws in the geometric algorithms, we propose a novel framework based on image-to-image translation to learn a pertinent mapping dependence for synthesizing straightened chromosomes with uninterrupted banding patterns and preserved details.

Image-to-Image Translation Translation

ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data

1 code implementation20 Aug 2020 Jiaming Zhang, Kailun Yang, Rainer Stiefelhagen

Ensuring the safety of all traffic participants is a prerequisite for bringing intelligent vehicles closer to practical applications.

Autonomous Vehicles Benchmarking +2

Adversarial Privacy-preserving Filter

2 code implementations25 Jul 2020 Jiaming Zhang, Jitao Sang, Xian Zhao, Xiaowen Huang, Yanfeng Sun, Yongli Hu

While widely adopted in practical applications, face recognition has been critically discussed regarding the malicious use of face images and the potential privacy problems, e. g., deceiving payment system and causing personal sabotage.

Adversarial Attack Face Recognition +1

Can we cover navigational perception needs of the visually impaired by panoptic segmentation?

no code implementations20 Jul 2020 Wei Mao, Jiaming Zhang, Kailun Yang, Rainer Stiefelhagen

Navigational perception for visually impaired people has been substantially promoted by both classic and deep learning based segmentation methods.

Deep Learning Instance Segmentation +2

Attention, Please! Adversarial Defense via Activation Rectification and Preservation

no code implementations24 Nov 2018 Shangxi Wu, Jitao Sang, Kaiyuan Xu, Jiaming Zhang, Jian Yu

This study provides a new understanding of the adversarial attack problem by examining the correlation between adversarial attack and visual attention change.

Adversarial Attack Adversarial Defense

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