Search Results for author:
Found 17 papers, 5 papers with code
Logic Traps in Evaluating Attribution Scores
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.
When to Go, and When to Explore: The Benefit of Post-Exploration in Intrinsic Motivation
Go-Explore achieved breakthrough performance on challenging reinforcement learning (RL) tasks with sparse rewards.
On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR
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.
Seq-Masks: Bridging the gap between appearance and gait modeling for video-based person re-identification
Validations on the gait recognition metric CASIA-B dataset further demonstrated the capability of our hybrid model.
LAVT: Language-Aware Vision Transformer for Referring Image Segmentation
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
Hierarchical interaction network for video object segmentation from referring expressions
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)
Optical Flow Estimation
Referring Expression Segmentation
+3
The Logic Traps in Evaluating Post-hoc Interpretations
Post-hoc interpretation aims to explain a trained model and reveal how the model arrives at a decision.
Potential-based Reward Shaping in Sokoban
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.
Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback
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.
Alignment Rationale for Natural Language Inference
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.
Transfer Learning and Curriculum Learning in Sokoban
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.
Explore User Neighborhood for Real-time E-commerce Recommendation
On the one hand, it utilizes UI relations and user neighborhood to capture both global and local information.
Helios: Heterogeneity-Aware Federated Learning with Dynamically Balanced Collaboration
In this paper, we propose Helios, a heterogeneity-aware FL framework to tackle the straggler issue.
Distributed, Parallel, and Cluster Computing
Anchor Diffusion for Unsupervised Video Object Segmentation
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)
Hetero-Center Loss for Cross-Modality Person Re-Identification
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.
Cross-Modality Person Re-identification
Person Re-Identification
Res-embedding for Deep Learning Based Click-Through Rate Prediction Modeling
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.
Learn to Interpret Atari Agents
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.
