Techniques

IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers NeurIPS 2021 ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform Interspeech 2021 IDARTS: Interactive Differentiable Architecture Search ICCV 2021 IIITH at SemEval-2021 Task 7: Leveraging transformer-based humourous and offensive text detection architectures using lexical and hurtlex features and task adaptive pretraining SemEval 2021 Image Harmonization With Transformer ICCV 2021 Image Inpainting Guided by Coherence Priors of Semantics and Textures CVPR 2021 Image Shape Manipulation From a Single Augmented Training Sample ICCV 2021 Image Super-Resolution With Non-Local Sparse Attention CVPR 2021 Implicit Filter-and-Sum Network for End-to-End Multi-Channel Speech Separation Interspeech 2021 Implicitly Abusive Comparisons – A New Dataset and Linguistic Analysis EACL 2021 Implicit Premise Generation with Discourse-aware Commonsense Knowledge Models EMNLP 2021 Improved pronunciation prediction accuracy using morphology ACL 2021 Improved Training of Generative Adversarial Networks Using Decision Forests WACV 2021 Improving Abstractive Dialogue Summarization with Hierarchical Pretraining and Topic Segment EMNLP 2021 Improving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies. ICML 2021 Improving Calibration through the Relationship with Adversarial Robustness NeurIPS 2021 Improving Channel Decorrelation for Multi-Channel Target Speech Extraction Interspeech 2021 Improving Compositional Generalization in Classification Tasks via Structure Annotations ACL 2021 Improving Deep Learning Interpretability by Saliency Guided Training NeurIPS 2021 Improving Generalization of Batch Whitening by Convolutional Unit Optimization ICCV 2021 Improving Gradient Flow with Unrolled Highway Expectation Maximization AAAI 2021 Improving Low-Precision Network Quantization via Bin Regularization ICCV 2021 Improving Math Word Problems with Pre-trained Knowledge and Hierarchical Reasoning EMNLP 2021 Improving Neural Machine Translation by Bidirectional Training EMNLP 2021 Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-Point ICCV 2021