no code implementations • 29 May 2024 • Hanwei Zhu, HaoNing Wu, Yixuan Li, ZiCheng Zhang, Baoliang Chen, Lingyu Zhu, Yuming Fang, Guangtao Zhai, Weisi Lin, Shiqi Wang
Extensive experiments on nine IQA datasets validate that the Compare2Score effectively bridges text-defined comparative levels during training with converted single image quality score for inference, surpassing state-of-the-art IQA models across diverse scenarios.
1 code implementation • 28 May 2024 • Xuefeng Du, Yiyou Sun, Yixuan Li
We employ a graph-theoretic approach, rigorously analyzing the separability of ID data from OOD data in a closed-form manner.
1 code implementation • 14 May 2024 • Zhimin Li, Jianwei Zhang, Qin Lin, Jiangfeng Xiong, Yanxin Long, Xinchi Deng, Yingfang Zhang, Xingchao Liu, Minbin Huang, Zedong Xiao, Dayou Chen, Jiajun He, Jiahao Li, Wenyue Li, Chen Zhang, Rongwei Quan, Jianxiang Lu, Jiabin Huang, Xiaoyan Yuan, Xiaoxiao Zheng, Yixuan Li, Jihong Zhang, Chao Zhang, Meng Chen, Jie Liu, Zheng Fang, Weiyan Wang, Jinbao Xue, Yangyu Tao, Jianchen Zhu, Kai Liu, Sihuan Lin, Yifu Sun, Yun Li, Dongdong Wang, Mingtao Chen, Zhichao Hu, Xiao Xiao, Yan Chen, Yuhong Liu, Wei Liu, Di Wang, Yong Yang, Jie Jiang, Qinglin Lu
For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images.
1 code implementation • 3 May 2024 • Hyeong Kyu Choi, Yixuan Li
Accordingly, we formalize the persona elicitation task, aiming to customize LLM behaviors to align with a target persona.
no code implementations • 2 May 2024 • Yifei Ming, Yixuan Li
Pre-trained contrastive vision-language models have demonstrated remarkable performance across a wide range of tasks.
no code implementations • 30 Apr 2024 • Jingbo Wang, Zhengyi Luo, Ye Yuan, Yixuan Li, Bo Dai
We address the challenge of content diversity and controllability in pedestrian simulation for driving scenarios.
no code implementations • 29 Apr 2024 • Yixuan Li, Dan C. Baciu, Marcos Novak, George Legrady
Over the past year, the emergence of advanced text-to-image Generative AI models has significantly impacted the art world, challenging traditional notions of creativity and the role of artists.
no code implementations • 20 Apr 2024 • Yixuan Li, Xuelin Liu, Xiaoyang Wang, Shiqi Wang, Weisi Lin
Therefore, we propose FakeBench, the first-of-a-kind benchmark towards transparent defake, consisting of fake images with human language descriptions on forgery signs.
no code implementations • 10 Apr 2024 • Yixuan Li, Weidong Yang, Ben Fei
Point cloud completion aims to generate a complete and high-fidelity point cloud from an initially incomplete and low-quality input.
no code implementations • 7 Apr 2024 • Zhen Fang, Yixuan Li, Feng Liu, Bo Han, Jie Lu
Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
1 code implementation • 29 Mar 2024 • Atsuyuki Miyai, Jingkang Yang, Jingyang Zhang, Yifei Ming, Qing Yu, Go Irie, Yixuan Li, Hai Li, Ziwei Liu, Kiyoharu Aizawa
This paper introduces a novel and significant challenge for Vision Language Models (VLMs), termed Unsolvable Problem Detection (UPD).
1 code implementation • 27 Mar 2024 • Shawn Im, Yixuan Li
Our work provides an initial attempt to theoretically analyze the learning dynamics of human preference alignment.
no code implementations • 6 Mar 2024 • Yixuan Li, Julian Parsert, Elizabeth Polgreen
In this paper, we evaluate the abilities of LLMs to solve formal synthesis benchmarks by carefully crafting a library of prompts for the domain.
no code implementations • 27 Feb 2024 • Bo Peng, Yadan Luo, Yonggang Zhang, Yixuan Li, Zhen Fang
Extensive experiments across OOD detection benchmarks empirically demonstrate that our proposed \textsc{ConjNorm} has established a new state-of-the-art in a variety of OOD detection setups, outperforming the current best method by up to 13. 25$\%$ and 28. 19$\%$ (FPR95) on CIFAR-100 and ImageNet-1K, respectively.
no code implementations • 22 Feb 2024 • Jiongxiao Wang, Jiazhao Li, Yiquan Li, Xiangyu Qi, Junjie Hu, Yixuan Li, Patrick McDaniel, Muhao Chen, Bo Li, Chaowei Xiao
Despite the general capabilities of Large Language Models (LLMs) like GPT-4 and Llama-2, these models still request fine-tuning or adaptation with customized data when it comes to meeting the specific business demands and intricacies of tailored use cases.
no code implementations • 13 Feb 2024 • Mingyang Li, Hongyu Liu, Yixuan Li, Zejun Wang, Yuan Yuan, Honglin Dai
Overall, this study successfully overcomes the challenge of missing data and provides valuable insights into early detection of Alzheimer's disease, demonstrating its unique research value and practical significance.
1 code implementation • 12 Feb 2024 • Yifei Ming, Haoyue Bai, Julian Katz-Samuels, Yixuan Li
Out-of-distribution (OOD) generalization is critical for machine learning models deployed in the real world.
1 code implementation • 5 Feb 2024 • Xuefeng Du, Zhen Fang, Ilias Diakonikolas, Yixuan Li
Harnessing the power of unlabeled in-the-wild data is non-trivial due to the heterogeneity of both in-distribution (ID) and OOD data.
no code implementations • 31 Jan 2024 • Rheeya Uppaal, Yixuan Li, Junjie Hu
In this work, we evaluate the utility of CPT for generative UDA.
1 code implementation • 23 Jan 2024 • Maxim Khanov, Jirayu Burapacheep, Yixuan Li
Aligning large language models with human objectives is paramount, yet common approaches including RLHF suffer from unstable and resource-intensive training.
no code implementations • 16 Jan 2024 • Yixuan Li, Peilin Chen, Hanwei Zhu, Keyan Ding, Leida Li, Shiqi Wang
The perceptual quality is quantified by the variant Mahalanobis Distance between the inner and outer Shape-Texture Statistics (DSTS), wherein the inner and outer statistics respectively describe the quality fingerprints of the distorted image and natural images.
no code implementations • 22 Dec 2023 • Soumya Suvra Ghosal, Yiyou Sun, Yixuan Li
Subspace learning yields highly distinguishable distance measures between ID and OOD data.
1 code implementation • 20 Dec 2023 • Yixuan Li, Archer Y. Yang, Ariane Marelli, Yue Li
This leads to a highly interpretable survival topic model that can infer PheCode-specific phenotype topics associated with patient mortality.
1 code implementation • 27 Nov 2023 • Zhenzhi Wang, Jingbo Wang, Yixuan Li, Dahua Lin, Bo Dai
Furthermore, we demonstrate that the distance between joint pairs for human-wise interactions can be generated using an off-the-shelf Large Language Model (LLM).
1 code implementation • NeurIPS 2023 • Yiyou Sun, Zhenmei Shi, Yixuan Li
Open-world semi-supervised learning aims at inferring both known and novel classes in unlabeled data, by harnessing prior knowledge from a labeled set with known classes.
1 code implementation • NeurIPS 2023 • Qizhou Wang, Zhen Fang, Yonggang Zhang, Feng Liu, Yixuan Li, Bo Han
Accordingly, we propose Distributional-Augmented OOD Learning (DAL), alleviating the OOD distribution discrepancy by crafting an OOD distribution set that contains all distributions in a Wasserstein ball centered on the auxiliary OOD distribution.
no code implementations • ICCV 2023 • Yixuan Li, Lihan Jiang, Linning Xu, Yuanbo Xiangli, Zhenzhi Wang, Dahua Lin, Bo Dai
While most of recent neural rendering works focus on objects and small-scale scenes, developing neural rendering methods for city-scale scenes is of great potential in many real-world applications.
1 code implementation • NeurIPS 2023 • Xuefeng Du, Yiyou Sun, Xiaojin Zhu, Yixuan Li
Utilizing auxiliary outlier datasets to regularize the machine learning model has demonstrated promise for out-of-distribution (OOD) detection and safe prediction.
no code implementations • 22 Sep 2023 • Pingyue Yue, Yixuan Li, Yue Li, Rui Zhang, Shuai Wang, Jianping An
Low Earth Orbit (LEO) satellites are being extensively researched in the development of secure Internet of Remote Things (IoRT).
no code implementations • 29 Aug 2023 • Wenxing Xu, Yuanchun Li, Jiacheng Liu, Yi Sun, Zhengyang Cao, Yixuan Li, Hao Wen, Yunxin Liu
Unlike cloud-based deep learning models that are often large and uniform, edge-deployed models usually demand customization for domain-specific tasks and resource-limited environments.
1 code implementation • 18 Aug 2023 • Yixuan Li, Huaping Liu, Qiang Jin, Miaomiao Cai, Peng Li
Optical Music Recognition (OMR) is an important technology in music and has been researched for a long time.
1 code implementation • 9 Aug 2023 • Yiyou Sun, Zhenmei Shi, YIngyu Liang, Yixuan Li
This paper bridges the gap by providing an analytical framework to formalize and investigate when and how known classes can help discover novel classes.
no code implementations • 15 Jun 2023 • Haoyue Bai, Gregory Canal, Xuefeng Du, Jeongyeol Kwon, Robert Nowak, Yixuan Li
Modern machine learning models deployed in the wild can encounter both covariate and semantic shifts, giving rise to the problems of out-of-distribution (OOD) generalization and OOD detection respectively.
1 code implementation • 15 Jun 2023 • Jingyang Zhang, Jingkang Yang, Pengyun Wang, Haoqi Wang, Yueqian Lin, Haoran Zhang, Yiyou Sun, Xuefeng Du, Kaiyang Zhou, Wayne Zhang, Yixuan Li, Ziwei Liu, Yiran Chen, Hai Li
Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 9 Jun 2023 • Yifei Ming, Yixuan Li
Recent CLIP-based fine-tuning methods such as prompt learning have demonstrated significant improvements in ID classification and OOD generalization where OOD labels are available.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
1 code implementation • 22 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.
no code implementations • 8 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.
no code implementations • 5 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
1 code implementation • 14 Apr 2023 • Yixuan Li, Bolin Chen, Baoliang Chen, Meng Wang, Shiqi Wang, Weisi Lin
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.
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.
1 code implementation • 10 Mar 2023 • Soumya Suvra Ghosal, Yixuan Li
Key to our framework, we consider soft group membership instead of hard group annotations.
1 code implementation • 6 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.
no code implementations • 2 Mar 2023 • Shuhang Zheng, Yixuan Li, Zhu Yu, Beinan Yu, Si-Yuan Cao, Minhang Wang, Jintao Xu, Rui Ai, Weihao Gu, Lun Luo, Hui-Liang Shen
The experimental results evaluated on the KITTI dataset show that, with only a small set of training data, I2P-Rec achieves recall rates at Top-1\% over 80\% and 90\%, when localizing monocular and stereo images on point cloud maps, respectively.
1 code implementation • ICCV 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.
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.
no code implementations • 8 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.
2 code implementations • 24 Nov 2022 • Yifei Ming, Ziyang Cai, Jiuxiang Gu, Yiyou Sun, Wei Li, Yixuan Li
Recognizing out-of-distribution (OOD) samples is critical for machine learning systems deployed in the open world.
1 code implementation • 14 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).
no code implementations • 26 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.
3 code implementations • 13 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.
no code implementations • 7 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.
no code implementations • 27 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.
1 code implementation • 21 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.
1 code implementation • 18 Aug 2022 • Mu Cai, Yixuan Li
In particular, generative models are shown to overly rely on the background information to estimate the likelihood.
1 code implementation • 4 Aug 2022 • Yiyou Sun, Yixuan Li
Machine learning models deployed in the wild naturally encounter unlabeled samples from both known and novel classes.
no code implementations • 26 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.
2 code implementations • 28 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
1 code implementation • 29 May 2022 • Xin Tong, Yixuan Li, Jiayi Li, Rongqi Bei, Luyao Zhang
Minority groups have been using social media to organize social movements that create profound social impacts.
2 code implementations • 19 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.
2 code implementations • 13 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.
1 code implementation • 17 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.
1 code implementation • CVPR 2022 • Xuefeng Du, Xin Wang, Gabriel Gozum, Yixuan Li
Building reliable object detectors that can detect out-of-distribution (OOD) objects is critical yet underexplored.
1 code implementation • 8 Mar 2022 • Yifei Ming, Yiyou Sun, Ousmane Dia, Yixuan Li
Out-of-distribution (OOD) detection is a critical task for reliable machine learning.
Out-of-Distribution Detection Out of Distribution (OOD) Detection +1
1 code implementation • 7 Feb 2022 • Julian Katz-Samuels, Julia Nakhleh, Robert Nowak, Yixuan Li
Out-of-distribution (OOD) detection is important for machine learning models deployed in the wild.
BIG-bench Machine Learning Out of Distribution (OOD) Detection
1 code implementation • 2 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.
1 code implementation • 26 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.
1 code implementation • 22 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.
1 code implementation • 1 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
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.
Ranked #13 on Out-of-Distribution Detection on ImageNet-1k vs SUN
1 code implementation • 18 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.
Ranked #4 on Out-of-Distribution Detection on ImageNet-1k vs SUN
1 code implementation • 26 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.
3 code implementations • 21 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.
no code implementations • 18 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.
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.
Ranked #12 on Out-of-Distribution Detection on ImageNet-1k vs SUN
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.
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.
1 code implementation • 12 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
1 code implementation • 14 Jun 2021 • Xuefeng Du, Tian Bian, Yu Rong, Bo Han, Tongliang Liu, Tingyang Xu, Wenbing Huang, Yixuan Li, Junzhou Huang
This paper bridges the gap by proposing a pairwise framework for noisy node classification on graphs, which relies on the PI as a primary learning proxy in addition to the pointwise learning from the noisy node class labels.
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.
1 code implementation • ICCV 2021 • Yixuan Li, Lei Chen, Runyu He, Zhenzhi Wang, Gangshan Wu, LiMin Wang
Spatio-temporal action detection is an important and challenging problem in video understanding.
4 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.
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
no code implementations • 1 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.
no code implementations • 1 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.
1 code implementation • ICCV 2021 • Mu Cai, Hong Zhang, Huijuan Huang, Qichuan Geng, Yixuan Li, Gao Huang
Image-to-image translation has been revolutionized with GAN-based methods.
6 code implementations • NeurIPS 2020 • Weitang Liu, XiaoYun Wang, John D. Owens, Yixuan Li
We propose a unified framework for OOD detection that uses an energy score.
no code implementations • 28 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
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.
1 code implementation • NeurIPS 2020 • Meng Zhou, Ziyu Liu, Pengwei Sui, Yixuan Li, Yuk Ying Chung
We present a multi-agent actor-critic method that aims to implicitly address the credit assignment problem under fully cooperative settings.
1 code implementation • 26 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
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
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.
Ranked #5 on Action Detection on UCF101-24
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.
no code implementations • 2 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.
4 code implementations • ECCV 2018 • Dhruv Mahajan, Ross Girshick, Vignesh Ramanathan, Kaiming He, Manohar Paluri, Yixuan Li, Ashwin Bharambe, Laurens van der Maaten
ImageNet classification is the de facto pretraining task for these models.
Ranked #222 on Image Classification on ImageNet (using extra training data)
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.
8 code implementations • ICLR 2018 • Shiyu Liang, Yixuan Li, R. Srikant
We show in a series of experiments that ODIN is compatible with diverse network architectures and datasets.
10 code implementations • 1 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.
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)
1 code implementation • 24 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.
no code implementations • 19 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.
1 code implementation • 25 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