Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate.
Finding local features that are repeatable across multiple views is a cornerstone of sparse 3D reconstruction.
A natural source for such attributes is the StyleSpace of StyleGAN, which is known to generate semantically meaningful dimensions in the image.
On the one hand, speaker adaptation methods fine-tune a trained multi-speaker text-to-speech (TTS) model with few enrolled samples.
Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks.
Ranked #1 on Image Classification on ImageNet (using extra training data)
In this paper, we present a FinRL-Meta framework that builds a universe of market environments for data-driven financial reinforcement learning.
In this paper, we ask the following question: is it possible to combine the strengths of CNNs and ViTs to build a light-weight and low latency network for mobile vision tasks?
Ranked #383 on Image Classification on ImageNet
Recommendation Algorithm大规模推荐算法库，包含推荐系统经典及最新算法LR、Wide&Deep、DSSM、TDM、MIND、Word2Vec、Bert4Rec、DeepWalk、SSR、GRU4Rec、Youtube_dnn、NCF、GNN、FM、FFM、DeepFM、DCN、DIN、DIEN、DLRM、MMOE、PLE、ESMM、MAML、xDeepFM、DeepFEFM、NFM、AFM、RALM、DMR、GateNet、NAML、DIFM、Deep Crossing、PNN、BST、AutoInt、FGCNN、FLEN、Fibinet、ListWise、DeepRec、ENSFM，TiSAS，AutoFIS等，包含经典推荐系统数据集criteo 、movielens等