163 citations · 304 across the 12 of their papers we have counts for
12 papers
Zero-th Order Algorithm for Softmax Attention Optimization
Yichuan Deng, Zhihang Li, Sridhar Mahadevan +1
Large language models (LLMs) have brought about significant transformations in human society. Among the crucial computations in LLMs, the softmax unit holds great importance. Its h…
Attention Scheme Inspired Softmax Regression
Yichuan Deng, Zhihang Li, Zhao Song
Large language models (LLMs) have made transformed changes for human society. One of the key computation in LLMs is the softmax unit. This operation is important in LLMs because it…
An Improved Sample Complexity for Rank-1 Matrix Sensing
Yichuan Deng, Zhihang Li, Zhao Song
Matrix sensing is a problem in signal processing and machine learning that involves recovering a low-rank matrix from a set of linear measurements. The goal is to reconstruct the o…
Solving Regularized Exp, Cosh and Sinh Regression Problems
Zhihang Li, Zhao Song, Tianyi Zhou
In modern machine learning, attention computation is a fundamental task for training large language models such as Transformer, GPT-4 and ChatGPT. In this work, we study exponentia…
Self-Supervised Modality-Aware Multiple Granularity Pre-Training for RGB-Infrared Person Re-Identification
Lin Wan, Qianyan Jing, Zongyuan Sun +3
RGB-Infrared person re-identification (RGB-IR ReID) aims to associate people across disjoint RGB and IR camera views. Currently, state-of-the-art performance of RGB-IR ReID is not…
G2DA: Geometry-Guided Dual-Alignment Learning for RGB-Infrared Person Re-Identification
Lin Wan, Zongyuan Sun, Qianyan Jing +3
RGB-Infrared (IR) person re-identification aims to retrieve person-of-interest from heterogeneous cameras, easily suffering from large image modality discrepancy caused by differen…
Neural Feature Search for RGB-Infrared Person Re-Identification
Yehansen Chen, Lin Wan, Zhihang Li +2
RGB-Infrared person re-identification (RGB-IR ReID) is a challenging cross-modality retrieval problem, which aims at matching the person-of-interest over visible and infrared camer…
ACFNet: Attentional Class Feature Network for Semantic Segmentation
Fan Zhang, Yanqin Chen, Zhihang Li +5
Recent works have made great progress in semantic segmentation by exploiting richer context, most of which are designed from a spatial perspective. In contrast to previous works, w…
PyramidBox++: High Performance Detector for Finding Tiny Face
Zhihang Li, Xu Tang, Junyu Han +2
With the rapid development of deep convolutional neural network, face detection has made great progress in recent years. WIDER FACE dataset, as a main benchmark, contributes greatl…
IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
Huaibo Huang, Zhihang Li, Ran He +2
We present a novel introspective variational autoencoder (IntroVAE) model for synthesizing high-resolution photographic images. IntroVAE is capable of self-evaluating the quality o…
Learning Disentangling and Fusing Networks for Face Completion Under Structured Occlusions
Zhihang Li, Yibo Hu, Ran He
Face completion aims to generate semantically new pixels for missing facial components. It is a challenging generative task due to large variations of face appearance. This paper s…
Recent Progress of Face Image Synthesis
Zhihe Lu, Zhihang Li, Jie Cao +2
Face synthesis has been a fascinating yet challenging problem in computer vision and machine learning. Its main research effort is to design algorithms to generate photo-realistic…