Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict. This goal is usually approached with attribution method, which assesses the influence of features on model predictions.
Go-Explore achieved breakthrough performance on challenging reinforcement learning (RL) tasks with sparse rewards.
Based on the above intuition, we first investigate types of end-to-end encoder-decoder based models in the single-input dual-output (SIDO) multi-task framework, after which a novel asynchronous decoding with fuzzy Pinyin sampling method is proposed according to the one-to-one correspondence characteristics between Pinyin and Character.
Validations on the gait recognition metric CASIA-B dataset further demonstrated the capability of our hybrid model.
Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image.
Ranked #1 on Referring Expression Segmentation on RefCOCO+ testA
In this paper, we investigate the problem of video object segmentation from referring expressions (VOSRE).
Ranked #1 on Referring Expression Segmentation on J-HMDB (Precision@0.9 metric)
While previous work has investigated the use of expert knowledge to generate potential functions, in this work, we study whether we can use a search algorithm(A*) to automatically generate a potential function for reward shaping in Sokoban, a well-known planning task.
The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few minutes to several days.
Deep learning models have achieved great success on the task of Natural Language Inference (NLI), though only a few attempts try to explain their behaviors.
In reinforcement learning, learning actions for a behavior policy that can be applied to new environments is still a challenge, especially for tasks that involve much planning.
On the one hand, it utilizes UI relations and user neighborhood to capture both global and local information.
In this paper, we propose Helios, a heterogeneity-aware FL framework to tackle the straggler issue.
Distributed, Parallel, and Cluster Computing
Unsupervised video object segmentation has often been tackled by methods based on recurrent neural networks and optical flow.
Ranked #7 on Unsupervised Video Object Segmentation on DAVIS 2016 (using extra training data)
With the joint supervision of Cross-Entropy (CE) loss and HC loss, the network is trained to achieve two vital objectives, inter-class discrepancy and intra-class cross-modality similarity as much as possible.
In this paper, we model user behavior using an interest delay model, study carefully the embedding mechanism, and obtain two important results: (i) We theoretically prove that small aggregation radius of embedding vectors of items which belongs to a same user interest domain will result in good generalization performance of deep CTR model.
In contrast to previous a-posteriori methods of visualizing DeepRL policies, we propose an end-to-end trainable framework based on Rainbow, a representative Deep Q-Network (DQN) agent.