There are 1 repository under aaai2021 topic.
[AAAI 2021] Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal
[AAAI'21] Robust Lightweight Facial Expression Recognition Network with Label Distribution Training
SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data (AAAI 2021)
Discovering New Intents with Deep Aligned Clustering (AAAI 2021)
[AAAI-2021, TKDE-2023] Official implementation for "Cross-Layer Distillation with Semantic Calibration".
Deep Open Intent Classification with Adaptive Decision Boundary (AAAI 2021)
Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies (AAAI 2021)
AttaNet for real-time semantic segmentation.
EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs (AAAI 2021)
Official PyTorch implementation of "Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning" (AAAI 2021)
Detecting Beneficial Feature Interactions for Recommender Systems, AAAI 2021
code for AAAI21 paper "Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion“
[AAAI'21] Code release for "Visual Pivoting for (Unsupervised) Entity Alignment".
Official Code of AAAI 2021 Paper "Multi-level Distance Regularization for Deep Metric Learning"
The unsupervised learning problem trains a diffeomorphic spatio-temporal grid, that registers the output sequence of the PDEs onto a non-uniform parameter/time-varying grid, such that the Kolmogorov n-width of the mapped data on the learned grid is minimized.
AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks
Supplementary material and code for "From Label Smoothing to Label Relaxation" as published at AAAI 2021.
PyTorch implementation of Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations (in AAAI 2021)
Python implementation of Mercer Features for Efficient Combinatorial Bayesian Optimization
A list of accepted papers in AAAI 2021 about anomaly detection.
Experiments for the paper ´An experimental study of the Transferability of spectral graph networks´
Code for the submission to the ML Reproducibility Challenge 2022, reproducing "If you like Shapley then you'll love the core"
The code for the paper "Weakly Supervised Deep Hyperspherical Quantization for Image Retrieval" (AAAI'21)
The L0-SIGN implementation.
Description of the system and its results that we developed as a part of our participation at CONSTRAINT shared task in AAAI-2021.
AAAI 2021: A Multi-step-ahead Markov Conditional Forward Model with Cube Perturbations for Extreme Weather Forecasting