117 citations · 178 across the 13 of their papers we have counts for
14 papers
Asymmetric Feature Fusion for Image Retrieval
Hui Wu, Min Wang, Wengang Zhou +2
In asymmetric retrieval systems, models with different capacities are deployed on platforms with different computational and storage resources. Despite the great progress, existing…
Supporting Energy-Based Learning With An Ising Machine Substrate: A Case Study on RBM
Uday Kumar Reddy Vengalam, Yongchao Liu, Tong Geng +2
Nature apparently does a lot of computation constantly. If we can harness some of that computation at an appropriate level, we can potentially perform certain type of computation (…
SimVQA: Exploring Simulated Environments for Visual Question Answering
Paola Cascante-Bonilla, Hui Wu, Letao Wang +2
Existing work on VQA explores data augmentation to achieve better generalization by perturbing the images in the dataset or modifying the existing questions and answers. While thes…
Learning Token-based Representation for Image Retrieval
Hui Wu, Min Wang, Wengang Zhou +2
In image retrieval, deep local features learned in a data-driven manner have been demonstrated effective to improve retrieval performance. To realize efficient retrieval on large i…
Contextual Similarity Aggregation with Self-attention for Visual Re-ranking
Jianbo Ouyang, Hui Wu, Min Wang +2
In content-based image retrieval, the first-round retrieval result by simple visual feature comparison may be unsatisfactory, which can be refined by visual re-ranking techniques.…
Separating Skills and Concepts for Novel Visual Question Answering
Spencer Whitehead, Hui Wu, Heng Ji +2
Generalization to out-of-distribution data has been a problem for Visual Question Answering (VQA) models. To measure generalization to novel questions, we propose to separate them…
Learning from Lexical Perturbations for Consistent Visual Question Answering
Spencer Whitehead, Hui Wu, Yi Ren Fung +3
Existing Visual Question Answering (VQA) models are often fragile and sensitive to input variations. In this paper, we propose a novel approach to address this issue based on modul…
Large Scale Neural Architecture Search with Polyharmonic Splines
Ulrich Finkler, Michele Merler, Rameswar Panda +8
Neural Architecture Search (NAS) is a powerful tool to automatically design deep neural networks for many tasks, including image classification. Due to the significant computationa…
NASTransfer: Analyzing Architecture Transferability in Large Scale Neural Architecture Search
Rameswar Panda, Michele Merler, Mayoore Jaiswal +8
Neural Architecture Search (NAS) is an open and challenging problem in machine learning. While NAS offers great promise, the prohibitive computational demand of most of the existin…
Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries
Fuwen Tan, Paola Cascante-Bonilla, Xiaoxiao Guo +3
This paper explores the task of interactive image retrieval using natural language queries, where a user progressively provides input queries to refine a set of retrieval results.…
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
Hui Wu, Yupeng Gao, Xiaoxiao Guo +4
Conversational interfaces for the detail-oriented retail fashion domain are more natural, expressive, and user friendly than classical keyword-based search interfaces. In this pape…
Dialog-based Interactive Image Retrieval
Xiaoxiao Guo, Hui Wu, Yu Cheng +3
Existing methods for interactive image retrieval have demonstrated the merit of integrating user feedback, improving retrieval results. However, most current systems rely on restri…
A Systematic Analysis for State-of-the-Art 3D Lung Nodule Proposals Generation
Hui Wu, Matrix Yao, Albert Hu +3
Lung nodule proposals generation is the primary step of lung nodule detection and has received much attention in recent years . In this paper, we first construct a model of 3-dimen…
S3Pool: Pooling with Stochastic Spatial Sampling
Shuangfei Zhai, Hui Wu, Abhishek Kumar +4
Feature pooling layers (e.g., max pooling) in convolutional neural networks (CNNs) serve the dual purpose of providing increasingly abstract representations as well as yielding com…