Generating Furry Cars: Disentangling Object Shape & Appearance across Multiple Domains
Comments Camera ready version for ICLR 2021
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Domain Generalization with MixStyle
Comments ICLR 2021; Code is available at https://github.com/KaiyangZhou/mixstyle-release
FedPandemic: A Cross-Device Federated Learning Approach Towards Elementary Prognosis of Diseases During a Pandemic
Comments 4+10 pages. To be presented at the DPML and MLPCP workshops at ICLR'21
Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation
Comments Published at ICLR 2021
INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving
Comments Published as a conference paper at ICLR 2021
Hidden Backdoor Attack against Semantic Segmentation Models
Comments This is a 6-pages short version of our ongoing work. It is accepted by the non-archival ICLR workshop on Security and Safety in Machine Learning Systems, 2021. The first two authors contributed equally to this work
Memory Optimization for Deep Networks
Comments 18 pages, ICLR'21
Learning Long-term Visual Dynamics with Region Proposal Interaction Networks
Comments ICLR 2021; Code: https://github.com/HaozhiQi/RPIN Website: https://haozhiqi.github.io/RPIN/ v5: update PHYRE results of each evaluation fold
Prediction of Tuberculosis using U-Net and segmentation techniques
Comments AI for Public Health Workshop at ICLR 2021. arXiv admin note: text overlap with arXiv:2007.02482
LiftPool: Bidirectional ConvNet Pooling
Comments published on ICLR 2021
Understanding the Effects of Data Parallelism and Sparsity on Neural Network Training
Comments ICLR 2021
Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study
Comments ICLR 2021. Project page: http://zhiqiangshen.com/projects/LS_and_KD/index.html
Optimizer Fusion: Efficient Training with Better Locality and Parallelism
Comments It is published as a paper at the Hardware Aware Efficient Training (HAET) workshop of ICLR 2021. There are 4 pages excluding references and appendices
xERTE: Explainable Reasoning on Temporal Knowledge Graphs for Forecasting Future Links
Comments 24 pages, 8 figures, accepted to ICLR 2021
SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness
Comments ICLR 2021
Modeling the Second Player in Distributionally Robust Optimization
Comments Accepted at ICLR 2021
Boost then Convolve: Gradient Boosting Meets Graph Neural Networks
Comments ICLR 2021: camera-ready
Bag of Tricks for Adversarial Training
Comments ICLR 2021
Individually Fair Gradient Boosting
Comments ICLR Camera-Ready Version
Benchmarks for Deep Off-Policy Evaluation
Comments ICLR 2021 paper. Policies and evaluation code are available at https://github.com/google-research/deep_ope
Continuous Weight Balancing
Comments 4 pages, 2 figures, presented at the S2D-OLAD workshop at ICLR 2021
Learning Neural Generative Dynamics for Molecular Conformation Generation
Comments Accepted by ICLR 2021. Code is available at \url{https://github.com/DeepGraphLearning/CGCF-ConfGen}
Shape-Texture Debiased Neural Network Training
Comments ICLR 2021. The code is available here: https://github.com/LiYingwei/ShapeTextureDebiasedTraining
High-Capacity Expert Binary Networks
Comments Accepted at ICLR 2021
DiffWave: A Versatile Diffusion Model for Audio Synthesis
Comments ICLR 2021 (oral)
Group Equivariant Generative Adversarial Networks
Comments Accepted by the International Conference on Learning Representations (ICLR) 2021
Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning
Comments ICLR 2021. Project page: http://dcl.csail.mit.edu/
Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity
Comments Accepted for publication in ICLR 2021
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation
Comments ICLR 2021. Project page: https://yuliang.vision/pseudo_seg/ Code: https://github.com/googleinterns/wss
Learning "What-if" Explanations for Sequential Decision-Making
Comments In Proc. 9th International Conference on Learning Representations (ICLR 2021)
