Search Results for author:
Found 14 papers, 4 papers with code
How to Inverting the Leverage Score Distribution?
Leverage score is a fundamental problem in machine learning and theoretical computer science.
Local Convergence of Approximate Newton Method for Two Layer Nonlinear Regression
Our main results involve analyzing the convergence properties of an approximate Newton method used to minimize the regularized training loss.
Zero-th Order Algorithm for Softmax Attention Optimization
We demonstrate the convergence of our algorithm, highlighting its effectiveness in efficiently computing gradients for large-scale LLMs.
Attention Scheme Inspired Softmax Regression
One of the key computation in LLMs is the softmax unit.
Solving Regularized Exp, Cosh and Sinh Regression Problems
In this paper, we make use of the input sparsity and purpose an algorithm that use $\log ( \|x_0 - x^*\|_2 / \epsilon)$ iterations and $\widetilde{O}(\mathrm{nnz}(A) + d^{\omega} )$ per iteration time to solve the problem.
Self-Supervised Modality-Aware Multiple Granularity Pre-Training for RGB-Infrared Person Re-Identification
Much of that is due to the notorious modality bias training issue brought by the single-modality ImageNet pre-training, which might yield RGB-biased representations that severely hinder the cross-modality image retrieval.
Contrastive Learning
Cross-Modality Person Re-identification
+3
G2DA: Geometry-Guided Dual-Alignment Learning for RGB-Infrared Person Re-Identification
Specifically, we propose to build a semantic-aligned complete graph into which all cross-modality images can be mapped via a pose-adaptive graph construction mechanism.
Neural Feature Search for RGB-Infrared Person Re-Identification
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 camera views.
GP-NAS: Gaussian Process Based Neural Architecture Search
(3) How to learn these correlations with a small number of samples?
ACFNet: Attentional Class Feature Network for Semantic Segmentation
Recent works have made great progress in semantic segmentation by exploiting richer context, most of which are designed from a spatial perspective.
PyramidBox++: High Performance Detector for Finding Tiny Face
With the rapid development of deep convolutional neural network, face detection has made great progress in recent years.
IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
On the other hand, the inference model is encouraged to classify between the generated and real samples while the generator tries to fool it as GANs.
Learning Disentangling and Fusing Networks for Face Completion Under Structured Occlusions
We treat the face completion and corruption as disentangling and fusing processes of clean faces and occlusions, and propose a jointly disentangling and fusing Generative Adversarial Network (DF-GAN).
Recent Progress of Face Image Synthesis
Face synthesis has been a fascinating yet challenging problem in computer vision and machine learning.
