Search Results for author: Zhipeng Cai

Found 26 papers, 12 papers with code

Globally Optimal and Efficient Vanishing Point Estimation in Atlanta World

no code implementations ECCV 2020 Haoang Li, Pyojin Kim, Ji Zhao, Kyungdon Joo, Zhipeng Cai, Zhe Liu , Yun-hui Liu

In Atlanta world, given a set of image lines, we aim to cluster them by the unknown-but-sought VPs whose number is unknown.

RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning

no code implementations17 Mar 2024 Javad Rafiei Asl, Prajwal Panzade, Eduardo Blanco, Daniel Takabi, Zhipeng Cai

In this paper, we introduce RobustSentEmbed, a self-supervised sentence embedding framework designed to improve both generalization and robustness in diverse text representation tasks and against a diverse set of adversarial attacks.

Contrastive Learning Semantic Textual Similarity +3

GIM: Learning Generalizable Image Matcher From Internet Videos

no code implementations16 Feb 2024 Xuelun Shen, Zhipeng Cai, Wei Yin, Matthias Müller, Zijun Li, Kaixuan Wang, Xiaozhi Chen, Cheng Wang

Given an architecture, GIM first trains it on standard domain-specific datasets and then combines it with complementary matching methods to create dense labels on nearby frames of novel videos.

Domain Generalization

I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption

no code implementations14 Feb 2024 Prajwal Panzade, Daniel Takabi, Zhipeng Cai

In today's machine learning landscape, fine-tuning pretrained transformer models has emerged as an essential technique, particularly in scenarios where access to task-aligned training data is limited.

Image Classification Privacy Preserving

MedBlindTuner: Towards Privacy-preserving Fine-tuning on Biomedical Images with Transformers and Fully Homomorphic Encryption

1 code implementation17 Jan 2024 Prajwal Panzade, Daniel Takabi, Zhipeng Cai

Advancements in machine learning (ML) have significantly revolutionized medical image analysis, prompting hospitals to rely on external ML services.

Privacy Preserving

CorresNeRF: Image Correspondence Priors for Neural Radiance Fields

1 code implementation NeurIPS 2023 Yixing Lao, Xiaogang Xu, Zhipeng Cai, Xihui Liu, Hengshuang Zhao

We present CorresNeRF, a novel method that leverages image correspondence priors computed by off-the-shelf methods to supervise NeRF training.

Novel View Synthesis Surface Reconstruction

LDM3D-VR: Latent Diffusion Model for 3D VR

no code implementations6 Nov 2023 Gabriela Ben Melech Stan, Diana Wofk, Estelle Aflalo, Shao-Yen Tseng, Zhipeng Cai, Michael Paulitsch, Vasudev Lal

Our models are fine-tuned from existing pretrained models on datasets containing panoramic/high-resolution RGB images, depth maps and captions.

Graph Convolutional Network with Connectivity Uncertainty for EEG-based Emotion Recognition

no code implementations22 Oct 2023 Hongxiang Gao, Xiangyao Wang, Zhenghua Chen, Min Wu, Zhipeng Cai, Lulu Zhao, Jianqing Li, Chengyu Liu

To address these challenges, this study introduces the distribution-based uncertainty method to represent spatial dependencies and temporal-spectral relativeness in EEG signals based on Graph Convolutional Network (GCN) architecture that adaptively assigns weights to functional aggregate node features, enabling effective long-path capturing while mitigating over-smoothing phenomena.

EEG Emotion Recognition

CLNeRF: Continual Learning Meets NeRF

1 code implementation ICCV 2023 Zhipeng Cai, Matthias Mueller

The source code, and the WAT dataset are available at https://github. com/IntelLabs/CLNeRF.

Continual Learning Novel View Synthesis

Resource-Adaptive Newton's Method for Distributed Learning

no code implementations20 Aug 2023 Shuzhen Chen, Yuan Yuan, Youming Tao, Zhipeng Cai, Dongxiao Yu

Distributed stochastic optimization methods based on Newton's method offer significant advantages over first-order methods by leveraging curvature information for improved performance.

Stochastic Optimization

Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image

1 code implementation ICCV 2023 Wei Yin, Chi Zhang, Hao Chen, Zhipeng Cai, Gang Yu, Kaixuan Wang, Xiaozhi Chen, Chunhua Shen

State-of-the-art (SOTA) monocular metric depth estimation methods can only handle a single camera model and are unable to perform mixed-data training due to the metric ambiguity.

Ranked #16 on Monocular Depth Estimation on NYU-Depth V2 (using extra training data)

Image Reconstruction Monocular Depth Estimation +1

Enhancing Worker Recruitment in Collaborative Mobile Crowdsourcing: A Graph Neural Network Trust Evaluation Approach

no code implementations7 Jun 2023 Zhongwei Zhan, Yingjie Wang, Peiyong Duan, Akshita Maradapu Vera Venkata Sai, Zhaowei Liu, Chaocan Xiang, Xiangrong Tong, Weilong Wang, Zhipeng Cai

The worker recruitment problem is modeled as an Undirected Complete Recruitment Graph (UCRG), for which a specific Tabu Search Recruitment (TSR) algorithm solution is proposed.

Edge-computing

Online Continual Learning Without the Storage Constraint

1 code implementation16 May 2023 Ameya Prabhu, Zhipeng Cai, Puneet Dokania, Philip Torr, Vladlen Koltun, Ozan Sener

In this paper, we target such applications, investigating the online continual learning problem under relaxed storage constraints and limited computational budgets.

Continual Learning

Revisiting Test Time Adaptation under Online Evaluation

1 code implementation10 Apr 2023 Motasem Alfarra, Hani Itani, Alejandro Pardo, Shyma Alhuwaider, Merey Ramazanova, Juan C. Pérez, Zhipeng Cai, Matthias Müller, Bernard Ghanem

To address this issue, we propose a more realistic evaluation protocol for TTA methods, where data is received in an online fashion from a constant-speed data stream, thereby accounting for the method's adaptation speed.

Test-time Adaptation

SimCS: Simulation for Domain Incremental Online Continual Segmentation

no code implementations29 Nov 2022 Motasem Alfarra, Zhipeng Cai, Adel Bibi, Bernard Ghanem, Matthias Müller

This work explores the problem of Online Domain-Incremental Continual Segmentation (ODICS), where the model is continually trained over batches of densely labeled images from different domains, with limited computation and no information about the task boundaries.

Autonomous Driving Continual Learning +2

Improving information retention in large scale online continual learning

no code implementations12 Oct 2022 Zhipeng Cai, Vladlen Koltun, Ozan Sener

The typical approach to address information retention (the ability to retain previous knowledge) is keeping a replay buffer of a fixed size and computing gradients using a mixture of new data and the replay buffer.

Continual Learning

A Black-box NLP Classifier Attacker

no code implementations22 Dec 2021 Yueyang Liu, Hunmin Lee, Zhipeng Cai

Deep neural networks have a wide range of applications in solving various real-world tasks and have achieved satisfactory results, in domains such as computer vision, image classification, and natural language processing.

Image Classification

Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data

1 code implementation ICCV 2021 Zhipeng Cai, Ozan Sener, Vladlen Koltun

We argue that "online" continual learning, where data is a single continuous stream without task boundaries, enables evaluating both information retention and online learning efficacy.

Continual Learning

Generative Adversarial Networks: A Survey Towards Private and Secure Applications

no code implementations7 Jun 2021 Zhipeng Cai, Zuobin Xiong, Honghui Xu, Peng Wang, Wei Li, Yi Pan

Generative Adversarial Networks (GAN) have promoted a variety of applications in computer vision, natural language processing, etc.

Collaborative City Digital Twin For Covid-19 Pandemic: A Federated Learning Solution

no code implementations5 Nov 2020 Junjie Pang, Jianbo Li, Zhenzhen Xie, Yan Huang, Zhipeng Cai

In this work, we propose a collaborative city digital twin based on FL, a novel paradigm that allowing multiple city DT to share the local strategy and status in a timely manner.

Federated Learning Management

Adversarial Privacy Preserving Graph Embedding against Inference Attack

1 code implementation30 Aug 2020 Kaiyang Li, Guangchun Luo, Yang Ye, Wei Li, Shihao Ji, Zhipeng Cai

In this paper, we propose Adversarial Privacy Graph Embedding (APGE), a graph adversarial training framework that integrates the disentangling and purging mechanisms to remove users' private information from learned node representations.

Graph Embedding Inference Attack +4

Consensus Maximization Tree Search Revisited

1 code implementation ICCV 2019 Zhipeng Cai, Tat-Jun Chin, Vladlen Koltun

First, we show that the consensus maximization tree structure used previously actually contains paths that connect nodes at both adjacent and non-adjacent levels.

Deterministic consensus maximization with biconvex programming

1 code implementation ECCV 2018 Zhipeng Cai, Tat-Jun Chin, Huu Le, David Suter

In this paper, we propose an efficient deterministic optimization algorithm for consensus maximization.

Robust Fitting in Computer Vision: Easy or Hard?

no code implementations ECCV 2018 Tat-Jun Chin, Zhipeng Cai, Frank Neumann

Robust model fitting plays a vital role in computer vision, and research into algorithms for robust fitting continues to be active.

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