← Techniques
Deep Learning › Techniques ›

Model Architecture

4351 directly classified papers

Papers per year

Papers

Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection CVPR 2020
Wide Hidden Expansion Layer for Deep Convolutional Neural Networks WACV 2020
Architecture Search of Dynamic Cells for Semantic Video Segmentation WACV 2020
Adapting Grad-CAM for Embedding Networks WACV 2020
Deep Adaptive Wavelet Network WACV 2020
SelectScale: Mining More Patterns from Images via Selective and Soft Dropout IJCAI 2020
G2RL: Geometry-Guided Representation Learning for Facial Action Unit Intensity Estimation IJCAI 2020
Position-Aware Recalibration Module: Learning From Feature Semantics and Feature Position IJCAI 2020
Multi-attention Meta Learning for Few-shot Fine-grained Image Recognition IJCAI 2020
Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation IJCAI 2020
Soft Threshold Ternary Networks IJCAI 2020
Reducing Underflow in Mixed Precision Training by Gradient Scaling IJCAI 2020
Cross-Interaction Hierarchical Attention Networks for Urban Anomaly Prediction IJCAI 2020
Training Neural Networks for and by Interpolation ICML 2020
Curvature-corrected learning dynamics in deep neural networks ICML 2020
Neural Architecture Search in A Proxy Validation Loss Landscape ICML 2020
Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression Based Speech Enhancement INTERSPEECH 2020
Harmonic Lowering for Accelerating Harmonic Convolution for Audio Signals INTERSPEECH 2020
A Multi-Scale Fusion Framework for Bimodal Speech Emotion Recognition INTERSPEECH 2020
AutoSpeech: Neural Architecture Search for Speaker Recognition INTERSPEECH 2020
Evolutionary Algorithm Enhanced Neural Architecture Search for Text-Independent Speaker Verification INTERSPEECH 2020
Neural Architecture Search on Acoustic Scene Classification INTERSPEECH 2020
Atss-Net: Target Speaker Separation via Attention-Based Neural Network INTERSPEECH 2020
Time-Domain Target-Speaker Speech Separation with Waveform-Based Speaker Embedding INTERSPEECH 2020
A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech INTERSPEECH 2020