TPAMI 2018 papers on Architectures and efficiency
16 of the 248 papers published in TPAMI 2018 (6.5%) are on Architectures and efficiency, compared with 3.1% at TPAMI 2017. They fall into 5 topics.
See TPAMI 2018 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
CNN design · 9 papers
- Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI (558 citations)
- ThiNet: Pruning CNN Filters for a Thinner Net (269 citations)
- Holistic CNN Compression via Low-Rank Decomposition with Knowledge Transfer (165 citations)
- Shallowing Deep Networks: Layer-Wise Pruning Based on Feature Representations (147 citations)
- Packing Convolutional Neural Networks in the Frequency Domain (88 citations)
- Deep Supervision with Intermediate Concepts (87 citations)
- Scattering Networks for Hybrid Representation Learning (86 citations)
- Runtime Network Routing for Efficient Image Classification (48 citations)
- Recurrent Convolutional Shape Regression (19 citations)
Pruning and efficient tuning · 2 papers
- Fine-Tuning CNN Image Retrieval with No Human Annotation (1,587 citations)
- Incremental Learning Through Deep Adaptation (273 citations)
Quantization · 2 papers
- Deep Neural Network Compression by In-Parallel Pruning-Quantization (149 citations)
- Composite Quantization (30 citations)
RNNs and normalization · 2 papers
- Discrete-Continuous Transformation Matching for Dense Semantic Correspondence (5 citations)
- Stay Connected (1 citation)
Attention and transformers · 1 paper
- Neural Machine Translation with Deep Attention (139 citations)
