Resolution Adaptive Networks for Eﬃcient Inference

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges (2021, methodology): “In general, the objective of SC is to generate a bottleneck whose data size is smaller than that of input data such as JPEG ile size of input data, which is in turn much smaller than data size of input tensor (32-bit loating point), as the communication delay is a key component to reduce overall inf”
Adaptive Focus for Efficient Video Recognition (2021, background): “Importantly, the patch ˜ v t is localized to capture the most informative re-conv”
A-ViT: Adaptive Tokens for Efficient Vision Transformer (2021, unknown): “One way is to change the architecture of the model to support adaptive computations [4,14,15, 18,25,27,30,37,42,51,54].”
Dynamic Network Quantization for Efficient Video Inference (2021, unknown): “Representative meth-ods for image classiﬁcation, dynamically adjust network depth [13, 33, 59, 21, 63], width [66, 7, 20], perform routing [26, 33] or switch resolutions [62].”