90 citations · 248 across the 15 of their papers we have counts for
15 papers
Efficient Matrix Implementation for Rotary Position Embedding
Chen Minqi, Zhongqi Yue, Shihao Zhang +5
Rotary Position Embedding (RoPE) has become a core component of modern Transformer architectures across language, vision, and 3D domains. However, existing implementations rely on…
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
Zeyi Huang, Andy Zhou, Zijian Lin +3
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…
Leveraging Large Language Models for Scalable Vector Graphics-Driven Image Understanding
Mu Cai, Zeyi Huang, Yuheng Li +3
Large language models (LLMs) have made significant advancements in natural language understanding. However, through that enormous semantic representation that the LLM has learnt, i…
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding
Minh-Long Luu, Zeyi Huang, Eric P. Xing +2
Mix-up training approaches have proven to be effective in improving the generalization ability of Deep Neural Networks. Over the years, the research community expands mix-up method…
Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation
Haohan Wang, Zeyi Huang, Xindi Wu +1
Data augmentation has been proven to be an effective technique for developing machine learning models that are robust to known classes of distributional shifts (e.g., rotations of…
The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization
Zeyi Huang, Haohan Wang, Dong Huang +2
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 t…
On the Integration of Self-Attention and Convolution
Xuran Pan, Chunjiang Ge, Rui Lu +4
Convolution and self-attention are two powerful techniques for representation learning, and they are usually considered as two peer approaches that are distinct from each other. In…
Toward Learning Human-aligned Cross-domain Robust Models by Countering Misaligned Features
Haohan Wang, Zeyi Huang, Hanlin Zhang +2
Machine learning has demonstrated remarkable prediction accuracy over i.i.d data, but the accuracy often drops when tested with data from another distribution. In this paper, we ai…
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition
Yulin Wang, Rui Huang, Shiji Song +2
Vision Transformers (ViT) have achieved remarkable success in large-scale image recognition. They split every 2D image into a fixed number of patches, each of which is treated as a…
Squared Norm as Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations
Haohan Wang, Zeyi Huang, Xindi Wu +1
Data augmentation is one of the most popular techniques for improving the robustness of neural networks. In addition to directly training the model with original samples and augmen…
Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection
Zeyi Huang, Yang Zou, Vijayakumar Bhagavatula +1
Weakly Supervised Object Detection (WSOD) has emerged as an effective tool to train object detectors using only the image-level category labels. However, without object-level label…
Self-Challenging Improves Cross-Domain Generalization
Zeyi Huang, Haohan Wang, Eric P. Xing +1
Convolutional Neural Networks (CNN) conduct image classification by activating dominant features that correlated with labels. When the training and testing data are under similar d…
Multiple Anchor Learning for Visual Object Detection
Wei Ke, Tianliang Zhang, Zeyi Huang +3
Classification and localization are two pillars of visual object detectors. However, in CNN-based detectors, these two modules are usually optimized under a fixed set of candidate…
Improving Object Detection with Inverted Attention
Zeyi Huang, Wei Ke, Dong Huang
Improving object detectors against occlusion, blur and noise is a critical step to deploy detectors in real applications. Since it is not possible to exhaust all image defects thro…
Large Margin Object Tracking with Circulant Feature Maps
Mengmeng Wang, Yong Liu, Zeyi Huang
Structured output support vector machine (SVM) based tracking algorithms have shown favorable performance recently. Nonetheless, the time-consuming candidate sampling and complex o…