Asia
Category-Extensible Out-of-Distribution Detection via Hierarchical Context Descriptions Supplementary Materials A Implementation Details
We also conduct empirical experiments to verify the effectiveness of those perturbations. As shown in Fig. A1, all of the perturbed text-features In addition, now that every perturbation can directly produce the description ( i.e., text-feature) of And the results are shown in Tab. OOD performance when the ID data is shifted. Table A2: Additionally improved ID accuracy on shifted datasets. Fig. A2, compared to the shifted ImageNet-A [ Sketch only preserve objects' shape and main texture, while the color information is totally vanished.
Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations
Fenglin Liu, Yuanxin Liu, Xuancheng Ren, Xiaodong He, Xu Sun
Neural Information Processing Systems http://nips.cc/
Transfer of Deep Reactive Policies for MDP Planning
Aniket (Nick) Bajpai, Sankalp Garg, None
Neural Information Processing Systems http://nips.cc/
We propose a post hoc saliency-based explanation framework for counterfactual reasoning in probabilistic multivariate time-series forecasting (regression) settings
Building upon Miller's framework of explanations derived from research in multiple
Boosting Black Box Variational Inference
Francesco Locatello, Gideon Dresdner, Rajiv Khanna, Isabel Valera, Gunnar Raetsch
Convex Optimizationwithout Projection Steps.arXivmath.OC, August 2011.
Hierarchically Gated Recurrent Neural Network for Sequence Modeling
Recently, there has been a renewed interest in using linear RNNs for efficient sequence modeling.
Re-randomized Densification for One Permutation Hashing and Bin-wise Consistent Weighted Sampling
Ping Li, Xiaoyun Li, Cun-Hui Zhang
Typically, hashing methods are essential for the use of Jaccard similarity tobepractical inlarge-scale settings.
On the Pareto Front of Multilingual Neural Machine Translation Liang Chen 1 Shuming Ma
In this work, we study how the performance of a given direction changes with its sampling ratio in Multilingual Neural Machine Translation (MNMT). By training over 200 multilingual models with various model sizes, data sizes, and language directions, we find it interesting that the performance of certain translation direction does not always improve with the increase of its weight in the multi-task optimization objective. Accordingly, scalarization method leads to a multitask trade-off front that deviates from the traditional Pareto front when there exists data imbalance in the training corpus, which poses a great challenge to improve the overall performance of all directions. Based on our observations, we propose the Double Power Law to predict the unique performance trade-off front in MNMT, which is robust across various languages, data adequacy, and the number of tasks. Finally, we formulate the sample ratio selection problem in MNMT as an optimization problem based on the Double Power Law. In our experiments, it achieves better performance than temperature searching and gradient manipulation methods with only 1/5 to 1/2 of the total training budget.