Novelty22
* *Dealing With the Novelty in Open Worlds
* Attention Guided Cosine Margin to Overcome Class-Imbalance in Few-Shot Road Object Detection
* Auto QA: The Question Is Not Only What, but Also Where
* Inductive Biases for Low Data VQA: A Data Augmentation Approach
* Reconstructive Training for Real-World Robustness in Image Classification
* Towards Unsupervised Online Domain Adaptation for Semantic Segmentation
* Uncertainty Aware Proposal Segmentation for Unknown Object Detection
* Unsupervised BatchNorm Adaptation (UBNA): A Domain Adaptation Method for Semantic Segmentation Without Using Source Domain Representations
* VQuAD: Video Question Answering Diagnostic Dataset
9 for Novelty22
Novelty23
* *Dealing With the Novelty in Open Worlds
* Is Meta-Learning Always Necessary?: A Practical ML Framework Solving Novel Tasks at Large-scale Car Sharing Platform
* k-NN embeded space conditioning for enhanced few-shot object detection
* MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration
* Phantom of Benchmark Dataset: Resolving Label Ambiguity Problem on Image Recognition in the Wild
* SOCAR: Socially-Obtained CAR Dataset for Image Recognition in the Wild
* Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation
7 for Novelty23