
-
Locally Masked Convolution for Autoregressive Models
High-dimensional generative models have many applications including imag...
read it
-
The Hanabi Challenge: A New Frontier for AI Research
From the early days of computing, games have been important testbeds for...
read it
-
Improving Lesion Segmentation for Diabetic Retinopathy using Adversarial Learning
Diabetic Retinopathy (DR) is a leading cause of blindness in working age...
read it
-
Mitigating Manipulation in Peer Review via Randomized Reviewer Assignments
We consider three important challenges in conference peer review: (i) re...
read it
-
Combining Deep Learning and Verification for Precise Object Instance Detection
Deep learning object detectors often return false positives with very hi...
read it
-
Embodied Multimodal Multitask Learning
Recent efforts on training visual navigation agents conditioned on langu...
read it
-
Self-training with Noisy Student improves ImageNet classification
We present a simple self-training method that achieves 87.4 on ImageNet,...
read it
-
A Theoretical Analysis of Contrastive Unsupervised Representation Learning
Recent empirical works have successfully used unlabeled data to learn fe...
read it
-
Interaction-Aware Multi-Agent Reinforcement Learning for Mobile Agents with Individual Goals
In a multi-agent setting, the optimal policy of a single agent is largel...
read it
-
Variational Auto-Decoder: Neural Generative Modeling from Partial Data
Learning a generative model from partial data (data with missingness) is...
read it
-
Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advances
Emotion is intrinsic to humans and consequently emotion understanding is...
read it
-
Transformer Dissection: An Unified Understanding for Transformer's Attention via the Lens of Kernel
Transformer is a powerful architecture that achieves superior performanc...
read it
-
Learning Spatial Awareness to Improve Crowd Counting
The aim of crowd counting is to estimate the number of people in images ...
read it
-
The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction
This paper studies the problem of predicting the distribution over multi...
read it
-
Driving in Dense Traffic with Model-Free Reinforcement Learning
Traditional planning and control methods could fail to find a feasible t...
read it
-
Factorized Multimodal Transformer for Multimodal Sequential Learning
The complex world around us is inherently multimodal and sequential (con...
read it
-
Optimization-Guided Binary Diversification to Mislead Neural Networks for Malware Detection
Motivated by the transformative impact of deep neural networks (DNNs) on...
read it
-
Person-in-WiFi: Fine-grained Person Perception using WiFi
Fine-grained person perception such as body segmentation and pose estima...
read it
-
A Deep Factorization of Style and Structure in Fonts
We propose a deep factorization model for typographic analysis that dise...
read it
-
Behavior Regularized Offline Reinforcement Learning
In reinforcement learning (RL) research, it is common to assume access t...
read it
-
Show Your Work: Improved Reporting of Experimental Results
Research in natural language processing proceeds, in part, by demonstrat...
read it
-
Learning the Difference that Makes a Difference with Counterfactually-Augmented Data
Despite alarm over the reliance of machine learning systems on so-called...
read it
-
The Non-IID Data Quagmire of Decentralized Machine Learning
Many large-scale machine learning (ML) applications need to train ML mod...
read it
-
Explosive Proofs of Mathematical Truths
Mathematical proofs are both paradigms of certainty and some of the most...
read it
-
Photosequencing of Motion Blur using Short and Long Exposures
Photosequencing aims to transform a motion blurred image to a sequence o...
read it
-
Single-Network Whole-Body Pose Estimation
We present the first single-network approach for 2D whole-body pose esti...
read it
-
Detecting Patterns of Physiological Response to Hemodynamic Stress via Unsupervised Deep Learning
Monitoring physiological responses to hemodynamic stress can help in det...
read it
-
Geometry-Aware Gradient Algorithms for Neural Architecture Search
Many recent state-of-the-art methods for neural architecture search (NAS...
read it
-
Few-Shot Learning with Intra-Class Knowledge Transfer
We consider the few-shot classification task with an unbalanced dataset,...
read it
-
Deep Reinforcement Learning Optimizes Graphene Nanopores for Efficient Desalination
Two-dimensional nanomaterials, such as graphene, have been extensively s...
read it
-
TarMAC: Targeted Multi-Agent Communication
We explore a collaborative multi-agent reinforcement learning setting wh...
read it
-
Online Model Distillation for Efficient Video Inference
High-quality computer vision models typically address the problem of und...
read it
-
UR-FUNNY: A Multimodal Language Dataset for Understanding Humor
Humor is a unique and creative communicative behavior displayed during s...
read it
-
A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text
When trained effectively, the Variational Autoencoder (VAE) is both a po...
read it
-
Adversary A3C for Robust Reinforcement Learning
Asynchronous Advantage Actor Critic (A3C) is an effective Reinforcement ...
read it
-
A Recommendation and Risk Classification System for Connecting Rough Sleepers to Essential Outreach Services
Rough sleeping is a chronic problem faced by some of the most disadvanta...
read it
-
Regularizing Black-box Models for Improved Interpretability
Most work on interpretability in machine learning has focused on designi...
read it
-
MAME : Model-Agnostic Meta-Exploration
Meta-Reinforcement learning approaches aim to develop learning procedure...
read it
-
Deep Multivariate Mixture of Gaussians for Object Detection under Occlusion
In this paper, we consider the problem of detecting object under occlusi...
read it
-
Estimating 3D Camera Pose from 2D Pedestrian Trajectories
We consider the task of re-calibrating the 3D pose of a static surveilla...
read it
-
Learning from Positive and Unlabeled Data by Identifying the Annotation Process
In binary classification, Learning from Positive and Unlabeled data (LeP...
read it
-
Minimizing FLOPs to Learn Efficient Sparse Representations
Deep representation learning has become one of the most widely adopted a...
read it
-
MultiImport: Inferring Node Importance in a Knowledge Graph from Multiple Input Signals
Given multiple input signals, how can we infer node importance in a know...
read it
-
Universal Inference Using the Split Likelihood Ratio Test
We propose a general method for constructing hypothesis tests and confid...
read it
-
TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting
We present a lightweight video motion retargeting approach TransMoMo tha...
read it
-
Towards Better Interpretability in Deep Q-Networks
Deep reinforcement learning techniques have demonstrated superior perfor...
read it
-
The Laplacian in RL: Learning Representations with Efficient Approximations
The smallest eigenvectors of the graph Laplacian are well-known to provi...
read it
-
Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels
Training deep networks for semantic segmentation requires annotation of ...
read it
-
Robustness of Conditional GANs to Noisy Labels
We study the problem of learning conditional generators from noisy label...
read it
-
Learning On-Road Visual Control for Self-Driving Vehicles with Auxiliary Tasks
A safe and robust on-road navigation system is a crucial component of ac...
read it