Deep Learning
PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining Y uting Gao
Large-scale vision-language pre-training has achieved promising results on downstream tasks.
Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL
Our goal is to learn an optimal policy that is also permutation invariant.
Deep Generative Model for Periodic Graphs
Their generative modeling has great potential in real-world applications such as material design and graphics synthesis. Classical models either rely on domain-specific predefined generation principles (e.g., in crystal net design),
Not All Bits have Equal Value: Heterogeneous Precisions via Trainable Noise
Y et, these methods fall short of providing a complete framework for producing efficient networks.
Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks Renan A. Rojas-Gomez T eck-Yian Lim Alexander G. Schwing Minh N. Do Raymond A. Y eh
LPS can be trained end-to-end from data and generalizes existing handcrafted downsampling layers. It is widely applicable as it can be integrated into any convolutional network by replacing down/upsampling layers. We evaluate LPS on image classification and semantic segmentation. Experiments show that LPS is on-par with or outperforms existing methods in both performance and shift consistency. For the first time, we achieve true shift-equivariance on semantic segmentation (P ASCAL VOC), i.e., 100% shift consistency, outperforming baselines by an absolute 3.3%.
MNIST Partition 1 MNIST Partition 2 MNIST Partition 2 (Permuted Labels) CIFAR - 10 Equally Initialized Parameters Client Gradient Update Label Heterogeneous Domain Heterogeneous! Local Training Steps
We extensively validate our method on both label-and domain-heterogeneous settings, on which it outperforms the state-of-the-art personalized federated learning methods.
