PinnedSik-Ho TsangSummary: My Paper Reading Lists, Tutorials & SharingsFrom Image Classification, Object Detection, NLP, Self-Supervised Learning, Semi-Supervised Learning, Vision-Language, GAN, SISR …Mar 15, 202012Mar 15, 202012
Sik-Ho TsangBrief Review — MogaNet: Multi-order Gated Aggregation NetworkMogaNet, Pure CNN Model2h ago2h ago
Sik-Ho TsangBrief Review — Fast Vision Transformer via Additive AttentionApply Fastformer Into Vision Transformer2d ago12d ago1
Sik-Ho TsangBrief Review —Audio-based snore detection using deep neural networksCQT + CNN + LSTM3d ago3d ago
Sik-Ho TsangBrief Review — Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model…Masked Modeling Duo (M2D), Self-Supervised Learning for Audio5d ago5d ago
Sik-Ho TsangBrief Review — More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using SparsitySLaK, with up to 61x61 convolutionsOct 1Oct 1
Sik-Ho TsangBrief Review — Fastformer: Additive Attention Can Be All You NeedAdditive Attention Mechanism, With Linear Complexity, Outperforms or On Par With Longformer, BigBird, LinformerSep 29Sep 29
Sik-Ho TsangBrief Review — A Snoring Sound Dataset for Body Position Recognition: Collection, Annotation, and…SSBPR Snore Sound DatasetSep 28Sep 28
Sik-Ho TsangBrief Review — SNIP: Single-Shot Network Pruning Based on Connection SensitivityOne of the Popular Model Pruning PapersSep 26Sep 26
Sik-Ho TsangBrief Review — Tiny Models are the Computational Saver for Large ModelsTinySaver, Adaptive Computational Reduction for Image ClassificationSep 24Sep 24