Search Results for author: Yixuan Li

Found 67 papers, 47 papers with code

Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection

1 code implementation22 May 2023 Rheeya Uppaal, Junjie Hu, Yixuan Li

Fine-tuning with pre-trained language models has been a de facto procedure to derive OOD detectors with respect to in-distribution (ID) data.

Out of Distribution (OOD) Detection

Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey

no code implementations8 May 2023 Ben Fei, Weidong Yang, Liwen Liu, Tianyue Luo, Rui Zhang, Yixuan Li, Ying He

Finally, we share our thoughts on some of the challenges and potential issues that future research in self-supervised learning for pre-training 3D point clouds may encounter.

Autonomous Driving Representation Learning +1

A Survey on Out-of-Distribution Detection in NLP

no code implementations5 May 2023 Hao Lang, Yinhe Zheng, Yixuan Li, Jian Sun, Fei Huang, Yongbin Li

Out-of-distribution (OOD) detection is essential for the reliable and safe deployment of machine learning systems in the real world.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Perceptual Quality Assessment of Face Video Compression: A Benchmark and An Effective Method

1 code implementation14 Apr 2023 Yixuan Li, Bolin Chen, Baoliang Chen, Meng Wang, Shiqi Wang

In this paper, we introduce the large-scale Compressed Face Video Quality Assessment (CFVQA) database, which is the first attempt to systematically understand the perceptual quality and diversified compression distortions in face videos.

Video Compression Video Quality Assessment +1

Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment

1 code implementation CVPR 2023 Yiyou Sun, Yaojie Liu, Xiaoming Liu, Yixuan Li, Wen-Sheng Chu

This work studies the generalization issue of face anti-spoofing (FAS) models on domain gaps, such as image resolution, blurriness and sensor variations.

Domain Generalization Face Anti-Spoofing +1

Distributionally Robust Optimization with Probabilistic Group

1 code implementation10 Mar 2023 Soumya Suvra Ghosal, Yixuan Li

Key to our framework, we consider soft group membership instead of hard group annotations.

Image Classification

Non-Parametric Outlier Synthesis

1 code implementation6 Mar 2023 Leitian Tao, Xuefeng Du, Xiaojin Zhu, Yixuan Li

Importantly, our proposed synthesis approach does not make any distributional assumption on the ID embeddings, thereby offering strong flexibility and generality.

Out of Distribution (OOD) Detection

I2P-Rec: Recognizing Images on Large-scale Point Cloud Maps through Bird's Eye View Projections

no code implementations2 Mar 2023 Yixuan Li, Shuhang Zheng, Zhu Yu, Beinan Yu, Si-Yuan Cao, Lun Luo, Hui-Liang Shen

Also, it can generalize well to unknown environments, achieving recall rates at Top-1\% over 80\% and 90\%, when localizing monocular images and stereo images on point cloud maps, respectively.

Depth Estimation

BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images

1 code implementation28 Feb 2023 Lun Luo, Shuhang Zheng, Yixuan Li, Yongzhi Fan, Beinan Yu, Siyuan Cao, HuiLiang Shen

The experiments conducted on large-scale public datasets show that our method 1) achieves state-of-the-art performance in terms of recall rates, 2) is robust to view changes, 3) shows strong generalization ability, and 4) can estimate the positions of query point clouds.

Retrieval

3D-Aware Face Swapping

no code implementations CVPR 2023 Yixuan Li, Chao Ma, Yichao Yan, Wenhan Zhu, Xiaokang Yang

To achieve this, we take advantage of the strong geometry and texture prior of 3D human faces, where the 2D faces are projected into the latent space of a 3D generative model.

Face Swapping

Logit Clipping for Robust Learning against Label Noise

no code implementations8 Dec 2022 Hongxin Wei, Huiping Zhuang, Renchunzi Xie, Lei Feng, Gang Niu, Bo An, Yixuan Li

In the presence of noisy labels, designing robust loss functions is critical for securing the generalization performance of deep neural networks.

Technological taxonomies for hypernym and hyponym retrieval in patent texts

no code implementations14 Nov 2022 You Zuo, Yixuan Li, Alma Parias García, Kim Gerdes

This paper presents an automatic approach to creating taxonomies of technical terms based on the Cooperative Patent Classification (CPC).

Retrieval

Is Out-of-Distribution Detection Learnable?

no code implementations26 Oct 2022 Zhen Fang, Yixuan Li, Jie Lu, Jiahua Dong, Bo Han, Feng Liu

Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.

Learning Theory Out-of-Distribution Detection +2

OpenOOD: Benchmarking Generalized Out-of-Distribution Detection

1 code implementation13 Oct 2022 Jingkang Yang, Pengyun Wang, Dejian Zou, Zitang Zhou, Kunyuan Ding, Wenxuan Peng, Haoqi Wang, Guangyao Chen, Bo Li, Yiyou Sun, Xuefeng Du, Kaiyang Zhou, Wayne Zhang, Dan Hendrycks, Yixuan Li, Ziwei Liu

Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications and has thus been extensively studied, with a plethora of methods developed in the literature.

Anomaly Detection Benchmarking +3

Novice Type Error Diagnosis with Natural Language Models

no code implementations7 Oct 2022 Chuqin Geng, Haolin Ye, Yixuan Li, Tianyu Han, Brigitte Pientka, Xujie Si

Strong static type systems help programmers eliminate many errors without much burden of supplying type annotations.

Language Modelling Vocal Bursts Type Prediction

How GPT-3 responds to different publics on climate change and Black Lives Matter: A critical appraisal of equity in conversational AI

no code implementations27 Sep 2022 Kaiping Chen, Anqi Shao, Jirayu Burapacheep, Yixuan Li

We traced these user experience divides to conversational differences and found that GPT-3 used more negative expressions when it responded to the education and opinion minority groups, compared to its responses to the majority groups.

Autonomous Driving Fairness

SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning

1 code implementation21 Sep 2022 Haobo Wang, Mingxuan Xia, Yixuan Li, YUREN MAO, Lei Feng, Gang Chen, Junbo Zhao

Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth.

Partial Label Learning Weakly-supervised Learning

Out-of-distribution Detection via Frequency-regularized Generative Models

1 code implementation18 Aug 2022 Mu Cai, Yixuan Li

In particular, generative models are shown to overly rely on the background information to estimate the likelihood.

Image Generation Out-of-Distribution Detection +1

OpenCon: Open-world Contrastive Learning

1 code implementation4 Aug 2022 Yiyou Sun, Yixuan Li

Machine learning models deployed in the wild naturally encounter unlabeled samples from both known and novel classes.

Contrastive Learning Representation Learning

Task Agnostic and Post-hoc Unseen Distribution Detection

no code implementations26 Jul 2022 Radhika Dua, Seongjun Yang, Yixuan Li, Edward Choi

Despite the recent advances in out-of-distribution(OOD) detection, anomaly detection, and uncertainty estimation tasks, there do not exist a task-agnostic and post-hoc approach.

Anomaly Detection Out of Distribution (OOD) Detection

POEM: Out-of-Distribution Detection with Posterior Sampling

1 code implementation28 Jun 2022 Yifei Ming, Ying Fan, Yixuan Li

In this work, we propose a novel posterior sampling-based outlier mining framework, POEM, which facilitates efficient use of outlier data and promotes learning a compact decision boundary between ID and OOD data for improved detection.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Mitigating Neural Network Overconfidence with Logit Normalization

2 code implementations19 May 2022 Hongxin Wei, Renchunzi Xie, Hao Cheng, Lei Feng, Bo An, Yixuan Li

Our method is motivated by the analysis that the norm of the logit keeps increasing during training, leading to overconfident output.

Out-of-Distribution Detection with Deep Nearest Neighbors

2 code implementations13 Apr 2022 Yiyou Sun, Yifei Ming, Xiaojin Zhu, Yixuan Li

In this paper, we explore the efficacy of non-parametric nearest-neighbor distance for OOD detection, which has been largely overlooked in the literature.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Are Vision Transformers Robust to Spurious Correlations?

1 code implementation17 Mar 2022 Soumya Suvra Ghosal, Yifei Ming, Yixuan Li

Deep neural networks may be susceptible to learning spurious correlations that hold on average but not in atypical test samples.

VOS: Learning What You Don't Know by Virtual Outlier Synthesis

1 code implementation2 Feb 2022 Xuefeng Du, Zhaoning Wang, Mu Cai, Yixuan Li

In this paper, we present VOS, a novel framework for OOD detection by adaptively synthesizing virtual outliers that can meaningfully regularize the model's decision boundary during training.

object-detection Object Detection +1

Interactive Image Inpainting Using Semantic Guidance

1 code implementation26 Jan 2022 Wangbo Yu, Jinhao Du, Ruixin Liu, Yixuan Li, Yuesheng Zhu

Image inpainting approaches have achieved significant progress with the help of deep neural networks.

Image Inpainting

PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning

1 code implementation22 Jan 2022 Haobo Wang, Ruixuan Xiao, Yixuan Li, Lei Feng, Gang Niu, Gang Chen, Junbo Zhao

Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation scenarios with label ambiguity.

Contrastive Learning Partial Label Learning +2

Provable Guarantees for Understanding Out-of-distribution Detection

1 code implementation1 Dec 2021 Peyman Morteza, Yixuan Li

Out-of-distribution (OOD) detection is important for deploying machine learning models in the real world, where test data from shifted distributions can naturally arise.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

ReAct: Out-of-distribution Detection With Rectified Activations

1 code implementation NeurIPS 2021 Yiyou Sun, Chuan Guo, Yixuan Li

Out-of-distribution (OOD) detection has received much attention lately due to its practical importance in enhancing the safe deployment of neural networks.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

DICE: Leveraging Sparsification for Out-of-Distribution Detection

1 code implementation18 Nov 2021 Yiyou Sun, Yixuan Li

Detecting out-of-distribution (OOD) inputs is a central challenge for safely deploying machine learning models in the real world.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges

1 code implementation26 Oct 2021 Mohammadreza Salehi, Hossein Mirzaei, Dan Hendrycks, Yixuan Li, Mohammad Hossein Rohban, Mohammad Sabokrou

To date, several research domains tackle the problem of detecting unfamiliar samples, including anomaly detection, novelty detection, one-class learning, open set recognition, and out-of-distribution detection.

Anomaly Detection Open Set Learning +1

Generalized Out-of-Distribution Detection: A Survey

2 code implementations21 Oct 2021 Jingkang Yang, Kaiyang Zhou, Yixuan Li, Ziwei Liu

In this survey, we first present a unified framework called generalized OOD detection, which encompasses the five aforementioned problems, i. e., AD, ND, OSR, OOD detection, and OD.

Anomaly Detection Autonomous Driving +4

Natural Attribute-based Shift Detection

no code implementations18 Oct 2021 Jeonghoon Park, Jimin Hong, Radhika Dua, Daehoon Gwak, Yixuan Li, Jaegul Choo, Edward Choi

Despite the impressive performance of deep networks in vision, language, and healthcare, unpredictable behaviors on samples from the distribution different than the training distribution cause severe problems in deployment.

Out of Distribution (OOD) Detection

On the Importance of Gradients for Detecting Distributional Shifts in the Wild

1 code implementation NeurIPS 2021 Rui Huang, Andrew Geng, Yixuan Li

Detecting out-of-distribution (OOD) data has become a critical component in ensuring the safe deployment of machine learning models in the real world.

Out of Distribution (OOD) Detection

Towards Unknown-aware Learning with Virtual Outlier Synthesis

no code implementations ICLR 2022 Xuefeng Du, Zhaoning Wang, Mu Cai, Yixuan Li

In this paper, we present VOS, a novel framework for OOD detection by adaptively synthesizing virtual outliers that can meaningfully regularize the model's decision boundary during training.

object-detection Object Detection +1

Can multi-label classification networks know what they don't know?

1 code implementation NeurIPS 2021 Haoran Wang, Weitang Liu, Alex Bocchieri, Yixuan Li

Our results show consistent improvement over previous methods that are based on the maximum-valued scores, which fail to capture joint information from multiple labels.

Classification Multi-class Classification +2

On the Impact of Spurious Correlation for Out-of-distribution Detection

1 code implementation12 Sep 2021 Yifei Ming, Hang Yin, Yixuan Li

Modern neural networks can assign high confidence to inputs drawn from outside the training distribution, posing threats to models in real-world deployments.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Can multi-label classification networks know what they don’t know?

1 code implementation NeurIPS 2021 Haoran Wang, Weitang Liu, Alex Bocchieri, Yixuan Li

Our results show consistent improvement over previous methods that are based on the maximum-valued scores, which fail to capture joint information from multiple labels.

Classification Multi-class Classification +2

MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space

3 code implementations CVPR 2021 Rui Huang, Yixuan Li

Detecting out-of-distribution (OOD) inputs is a central challenge for safely deploying machine learning models in the real world.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

MOOD: Multi-level Out-of-distribution Detection

1 code implementation CVPR 2021 Ziqian Lin, Sreya Dutta Roy, Yixuan Li

Out-of-distribution (OOD) detection is essential to prevent anomalous inputs from causing a model to fail during deployment.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Beyond the Pixels: Exploring the Effects of Bit-Level Network and File Corruptions on Video Model Robustness

no code implementations1 Jan 2021 Trenton Chang, Daniel Yang Fu, Yixuan Li

We investigate the robustness of video machine learning models to bit-level network and file corruptions, which can arise from network transmission failures or hardware errors, and explore defenses against such corruptions.

Action Recognition Multi-Object Tracking

Energy-based Out-of-distribution Detection for Multi-label Classification

no code implementations1 Jan 2021 Haoran Wang, Weitang Liu, Alex Bocchieri, Yixuan Li

Our results show consistent improvement over previous methods that are based on the maximum-valued scores, which fail to capture joint information from multiple labels.

Classification General Classification +4

Informative Outlier Matters: Robustifying Out-of-distribution Detection Using Outlier Mining

no code implementations28 Sep 2020 Jiefeng Chen, Yixuan Li, Xi Wu, YIngyu Liang, Somesh Jha

We show that, by mining informative auxiliary OOD data, one can significantly improve OOD detection performance, and somewhat surprisingly, generalize to unseen adversarial attacks.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Model Patching: Closing the Subgroup Performance Gap with Data Augmentation

1 code implementation ICLR 2021 Karan Goel, Albert Gu, Yixuan Li, Christopher Ré

Particularly concerning are models with inconsistent performance on specific subgroups of a class, e. g., exhibiting disparities in skin cancer classification in the presence or absence of a spurious bandage.

Data Augmentation Skin Cancer Classification

ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining

1 code implementation26 Jun 2020 Jiefeng Chen, Yixuan Li, Xi Wu, YIngyu Liang, Somesh Jha

We show that, by mining informative auxiliary OOD data, one can significantly improve OOD detection performance, and somewhat surprisingly, generalize to unseen adversarial attacks.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Robust Out-of-distribution Detection for Neural Networks

1 code implementation AAAI Workshop AdvML 2022 Jiefeng Chen, Yixuan Li, Xi Wu, YIngyu Liang, Somesh Jha

Formally, we extensively study the problem of Robust Out-of-Distribution Detection on common OOD detection approaches, and show that state-of-the-art OOD detectors can be easily fooled by adding small perturbations to the in-distribution and OOD inputs.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Actions as Moving Points

2 code implementations ECCV 2020 Yixuan Li, Zixu Wang, Li-Min Wang, Gangshan Wu

The existing action tubelet detectors often depend on heuristic anchor design and placement, which might be computationally expensive and sub-optimal for precise localization.

Action Detection Action Recognition

Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Search

no code implementations CVPR 2019 Abhimanyu Dubey, Laurens van der Maaten, Zeki Yalniz, Yixuan Li, Dhruv Mahajan

Empirical evaluations of this defense strategy on ImageNet suggest that it is very effective in attack settings in which the adversary does not have access to the image database.

Enhancing Stock Market Prediction with Extended Coupled Hidden Markov Model over Multi-Sourced Data

no code implementations2 Sep 2018 Xi Zhang, Yixuan Li, Senzhang Wang, Binxing Fang, Philip S. Yu

In this work, we study how to explore multiple data sources to improve the performance of the stock prediction.

Stock Prediction

Understanding the Loss Surface of Neural Networks for Binary Classification

no code implementations ICML 2018 Shiyu Liang, Ruoyu Sun, Yixuan Li, R. Srikant

Here we focus on the training performance of single-layered neural networks for binary classification, and provide conditions under which the training error is zero at all local minima of a smooth hinge loss function.

Binary Classification Classification +1

Snapshot Ensembles: Train 1, get M for free

9 code implementations1 Apr 2017 Gao Huang, Yixuan Li, Geoff Pleiss, Zhuang Liu, John E. Hopcroft, Kilian Q. Weinberger

In this paper, we propose a method to obtain the seemingly contradictory goal of ensembling multiple neural networks at no additional training cost.

Stacked Generative Adversarial Networks

2 code implementations CVPR 2017 Xun Huang, Yixuan Li, Omid Poursaeed, John Hopcroft, Serge Belongie

In this paper, we propose a novel generative model named Stacked Generative Adversarial Networks (SGAN), which is trained to invert the hierarchical representations of a bottom-up discriminative network.

Ranked #11 on Conditional Image Generation on CIFAR-10 (Inception score metric)

Conditional Image Generation

Convergent Learning: Do different neural networks learn the same representations?

1 code implementation24 Nov 2015 Yixuan Li, Jason Yosinski, Jeff Clune, Hod Lipson, John Hopcroft

Recent success in training deep neural networks have prompted active investigation into the features learned on their intermediate layers.

Deep Manifold Traversal: Changing Labels with Convolutional Features

no code implementations19 Nov 2015 Jacob R. Gardner, Paul Upchurch, Matt J. Kusner, Yixuan Li, Kilian Q. Weinberger, Kavita Bala, John E. Hopcroft

Many tasks in computer vision can be cast as a "label changing" problem, where the goal is to make a semantic change to the appearance of an image or some subject in an image in order to alter the class membership.

Uncovering the Small Community Structure in Large Networks: A Local Spectral Approach

1 code implementation25 Sep 2015 Yixuan Li, Kun He, David Bindel, John Hopcroft

Nowadays, as we often explore networks with billions of vertices and find communities of size hundreds, it is crucial to shift our attention from macroscopic structure to microscopic structure when dealing with large networks.

Social and Information Networks Data Structures and Algorithms Physics and Society G.2.2; H.3.3

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