no code implementations • 27 Dec 2023 • Guansong Lu, Yuanfan Guo, Jianhua Han, Minzhe Niu, Yihan Zeng, Songcen Xu, Zeyi Huang, Zhao Zhong, Wei zhang, Hang Xu
Current large-scale diffusion models represent a giant leap forward in conditional image synthesis, capable of interpreting diverse cues like text, human poses, and edges.
1 code implementation • ICCV 2023 • Zeyi Huang, Andy Zhou, Zijian Lin, Mu Cai, Haohan Wang, Yong Jae Lee
Domain generalization studies the problem of training a model with samples from several domains (or distributions) and then testing the model with samples from a new, unseen domain.
Ranked #15 on Domain Generalization on PACS
no code implementations • 9 Jun 2023 • Mu Cai, Zeyi Huang, Yuheng Li, Haohan Wang, Yong Jae Lee
By leveraging the XML-based textual descriptions of SVG representations instead of raster images, we aim to bridge the gap between the visual and textual modalities, allowing LLMs to directly understand and manipulate images without the need for parameterized visual components.
1 code implementation • 9 Dec 2022 • Minh-Long Luu, Zeyi Huang, Eric P. Xing, Yong Jae Lee, Haohan Wang
Mix-up training approaches have proven to be effective in improving the generalization ability of Deep Neural Networks.
Ranked #1 on Classifier calibration on CIFAR-100
1 code implementation • 4 Jun 2022 • Haohan Wang, Zeyi Huang, Xindi Wu, Eric P. Xing
Finally, we test this simple technique we identify (worst-case data augmentation with squared l2 norm alignment regularization) and show that the benefits of this method outrun those of the specially designed methods.
1 code implementation • 9 Apr 2022 • Zeyi Huang, Haohan Wang, Dong Huang, Yong Jae Lee, Eric P. Xing
Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e. g., generalization across distributions) is valued.
no code implementations • CVPR 2022 • Zeyi Huang, Haohan Wang, Dong Huang, Yong Jae Lee, Eric P. Xing
Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e. g., generalization across distributions) is valued.
2 code implementations • CVPR 2022 • Xuran Pan, Chunjiang Ge, Rui Lu, Shiji Song, Guanfu Chen, Zeyi Huang, Gao Huang
In this paper, we show that there exists a strong underlying relation between them, in the sense that the bulk of computations of these two paradigms are in fact done with the same operation.
1 code implementation • 5 Nov 2021 • Haohan Wang, Zeyi Huang, HANLIN ZHANG, Yong Jae Lee, Eric Xing
Machine learning has demonstrated remarkable prediction accuracy over i. i. d data, but the accuracy often drops when tested with data from another distribution.
2 code implementations • NeurIPS 2021 • Yulin Wang, Rui Huang, Shiji Song, Zeyi Huang, Gao Huang
Inspired by this phenomenon, we propose a Dynamic Transformer to automatically configure a proper number of tokens for each input image.
Ranked #29 on Image Classification on CIFAR-100 (using extra training data)
no code implementations • 1 Jan 2021 • Haohan Wang, Zeyi Huang, Xindi Wu, Eric Xing
Data augmentation is one of the most popular techniques for improving the robustness of neural networks.
no code implementations • 1 Jan 2021 • Haohan Wang, Zeyi Huang, Eric Xing
In this paper, we formally study the generalization error bound for this setup with the knowledge of how the spurious features are associated with the label.
1 code implementation • 25 Nov 2020 • Haohan Wang, Zeyi Huang, Xindi Wu, Eric P. Xing
Data augmentation is one of the most popular techniques for improving the robustness of neural networks.
1 code implementation • NeurIPS 2020 • Zeyi Huang, Yang Zou, Vijayakumar Bhagavatula, Dong Huang
Moreover, the image-level category labels do not enforce consistent object detection across different transformations of the same images.
Ranked #1 on Weakly Supervised Object Detection on MSCOCO
8 code implementations • ECCV 2020 • Zeyi Huang, Haohan Wang, Eric P. Xing, Dong Huang
We introduce a simple training heuristic, Representation Self-Challenging (RSC), that significantly improves the generalization of CNN to the out-of-domain data.
Ranked #27 on Domain Generalization on PACS
3 code implementations • CVPR 2020 • Wei Ke, Tianliang Zhang, Zeyi Huang, Qixiang Ye, Jianzhuang Liu, Dong Huang
In this paper, we propose a Multiple Instance Learning (MIL) approach that selects anchors and jointly optimizes the two modules of a CNN-based object detector.
Ranked #116 on Object Detection on COCO test-dev
1 code implementation • 28 May 2019 • Haohan Wang, Xindi Wu, Zeyi Huang, Eric P. Xing
We investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN).
1 code implementation • 28 Mar 2019 • Zeyi Huang, Wei Ke, Dong Huang
Our approach (1) operates along both the spatial and channels dimensions of the feature maps; (2) requires no extra training on hard samples, no extra network parameters for attention estimation, and no testing overheads.
no code implementations • CVPR 2017 • Mengmeng Wang, Yong liu, Zeyi Huang
Structured output support vector machine (SVM) based tracking algorithms have shown favorable performance recently.