Search Results for author:
Found 8 papers, 7 papers with code
LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory
Transformer models have been successful in various sequence processing tasks, but the self-attention mechanism's computational cost limits its practicality for long sequences.
Switch EMA: A Free Lunch for Better Flatness and Sharpness
Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DNN) optimization.
Masked Modeling for Self-supervised Representation Learning on Vision and Beyond
As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and the low dependence on labeled data.
SemiReward: A General Reward Model for Semi-supervised Learning
The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias.
OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
Spatio-temporal predictive learning is a learning paradigm that enables models to learn spatial and temporal patterns by predicting future frames from given past frames in an unsupervised manner.
MogaNet: Multi-order Gated Aggregation Network
Notably, MogaNet hits 80. 0\% and 87. 8\% accuracy with 5. 2M and 181M parameters on ImageNet-1K, outperforming ParC-Net and ConvNeXt-L, while saving 59\% FLOPs and 17M parameters, respectively.
Ranked #1 on
Pose Estimation
on COCO val2017
OpenMixup: A Comprehensive Mixup Benchmark for Visual Classification
Data mixing, or mixup, is a data-dependent augmentation technique that has greatly enhanced the generalizability of modern deep neural networks.
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
Accordingly, we propose $\eta$-balanced mixup loss for complementary learning of the two sub-objectives.
Ranked #7 on
Image Classification
on Places205
