← Techniques
Deep Learning › Techniques ›

Model Architecture

4351 directly classified papers

Papers per year

Papers

Improving Interpretability of Deep Neural Networks With Semantic Information CVPR 2017
Active Convolution: Learning the Shape of Convolution for Image Classification CVPR 2017
Fixed-Point Factorized Networks CVPR 2017
Gated Feedback Refinement Network for Dense Image Labeling CVPR 2017
A Deep Regression Architecture With Two-Stage Re-Initialization for High Performance Facial Landmark Detection CVPR 2017
Differentiable Learning of Submodular Models NIPS 2017
Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade CVPR 2017
Training Quantized Nets: A Deeper Understanding NIPS 2017
Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning NIPS 2017
Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon NIPS 2017
Compression-aware Training of Deep Networks NIPS 2017
Kernel Pooling for Convolutional Neural Networks CVPR 2017
CLKN: Cascaded Lucas-Kanade Networks for Image Alignment CVPR 2017
SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability NIPS 2017
Deep View Morphing CVPR 2017
Feature Pyramid Networks for Object Detection CVPR 2017
Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks NIPS 2017
Aggregated Residual Transformations for Deep Neural Networks CVPR 2017
Net-Trim: Convex Pruning of Deep Neural Networks with Performance Guarantee NIPS 2017
EigenNet: Towards Fast and Structural Learning of Deep Neural Networks IJCAI 2017
Xception: Deep Learning With Depthwise Separable Convolutions CVPR 2017
Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples NIPS 2017
The Reversible Residual Network: Backpropagation Without Storing Activations NIPS 2017
Learning Efficient Object Detection Models with Knowledge Distillation NIPS 2017
Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks NIPS 2017