paper-with-me

Papers Image Deep Networks

“Image Deep Networks” 태그가 달린 논문 3편 · 필터 해제

Video prediction using score-based conditional density estimation

2024-10-30 · Pierre-Étienne H. Fiquet, Eero P. Simoncelli

Temporal prediction is inherently uncertain, but representing the ambiguity in natural image sequences is a challenging high-dimensional probabilistic inference problem. For natural scenes, the curse of dimensionality re…

Density EstimationImage Deep NetworksPredictionVideo Prediction

Demystify Transformers & Convolutions in Modern Image Deep Networks

2022-11-10 · Xiaowei Hu, Min Shi, Weiyun Wang, Sitong Wu 외

Vision transformers have gained popularity recently, leading to the development of new vision backbones with improved features and consistent performance gains. However, these advancements are not solely attributable to …

Adversarial RobustnessImage Deep NetworksSpatial Token Mixer

Stochastic regularized majorization-minimization with weakly convex and multi-convex surrogates

2022-01-05 · Hanbaek Lyu

Stochastic majorization-minimization (SMM) is a class of stochastic optimization algorithms that proceed by sampling new data points and minimizing a recursive average of surrogate functions of an objective function. The…

Dictionary LearningImage Deep NetworksStochastic OptimizationTensor Decomposition
1–3 / 3