Latest Research
Ranking Policy Gradient
To accelerate the learning of policy gradient methods, we describe a novel off-policy learning framework and establish the equivalence between maximizing the lower bound of return and imitating a near-optimal policy without accessing any oracles.
Cascade R-CNN: High Quality Object Detection and Instance Segmentation
In object detection, the intersection over union (IoU) threshold is frequently used to define positives/negatives.
#17 best model for
Object Detection
on COCO
INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION
LIAAD at SemDeep-5 Challenge: Word-in-Context (WiC)
This paper describes the LIAAD system that was ranked second place in the Word-in-Context challenge (WiC) featured in SemDeep-5.
Adversarial Computation of Optimal Transport Maps
We show that during training, our generator follows the $W_2$-geodesic between the initial and the target distributions.
Business Taxonomy Construction Using Concept-Level Hierarchical Clustering
• SenticNet/neeq-annual-reports
Business taxonomies are indispensable tools for investors to do equity research and make professional decisions.
ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation
The whole network has nearly symmetric architecture, which is mainly composed of a series of factorized convolution unit (FCU) and its parallel counterparts (PFCU).
#5 best model for
Real-Time Semantic Segmentation
on Cityscapes
Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression
We demonstrate the power of CCNs for entropy modeling in both lossless and lossy image compression.
Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation
Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings.
LANGUAGE MODELLING WORD EMBEDDINGS WORD SENSE DISAMBIGUATION
Densely Connected Search Space for More Flexible Neural Architecture Search
We achieve this by constructing a densely connected search space and name our method as DenseNAS.
#27 best model for
Image Classification
on ImageNet
Variational Sequential Labelers for Semi-Supervised Learning
Our model family consists of a latent-variable generative model and a discriminative labeler.