Skip to search formSkip to main contentSkip to account menu
  • Publications
  • Influence
DivideMix: Learning with Noisy Labels as Semi-supervised Learning
TLDR
This work proposes DivideMix, a novel framework for learning with noisy labels by leveraging semi-supervised learning techniques, which models the per-sample loss distribution with a mixture model to dynamically divide the training data into a labeled set with clean samples and an unlabeled set with noisy samples.
View PDF on arXiv
AR-miner: mining informative reviews for developers from mobile app marketplace
TLDR
This work presents “AR-Miner” — a novel computational framework for App Review Mining, which performs comprehensive analytics from raw user reviews by first extracting informativeuser reviews by filtering noisy and irrelevant ones, then grouping the informative reviews automatically using topic modeling, and finally presenting the groups of most “informative” reviews via an intuitive visualization approach.
View on ACM
Reliable Patch Trackers: Robust visual tracking by exploiting reliable patches
TLDR
A tracking reliability metric is presented to measure how reliably a patch can be tracked, where a probability model is proposed to estimate the distribution of reliable patches under a sequential Monte Carlo framework.
View on IEEE
Prototypical Contrastive Learning of Unsupervised Representations
TLDR
This paper introduces prototypes as latent variables to help find the maximum-likelihood estimation of the network parameters in an Expectation-Maximization framework and proposes ProtoNCE loss, a generalized version of the InfoN CE loss for contrastive learning, which encourages representations to be closer to their assigned prototypes.
View PDF on arXiv
Deep Learning for Content-Based Image Retrieval: A Comprehensive Study
TLDR
This paper investigates a framework of deep learning with application to CBIR tasks with an extensive set of empirical studies by examining a state-of-the-art deep learning method (Convolutional Neural Networks) for CBIr tasks under varied settings.
View on ACM
Online AUC Maximization
TLDR
This work develops online learning algorithm for maximizing Area Under the ROC curve (AUC), a metric that is widely used for measuring the classification performance for imbalanced data distributions, and presents two algorithms for online AUC maximization with theoretic performance guarantee.
View Paper
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
TLDR
This paper introduces a contrastive loss to ALign the image and text representations BEfore Fusing through cross-modal attention, which enables more grounded vision and language representation learning and proposes momentum distillation, a self-training method which learns from pseudo-targets produced by a momentum model.
View PDF on arXiv
Learning Distance Metrics with Contextual Constraints for Image Retrieval
TLDR
Experimental results show that the proposed algorithms for Discriminative Component Analysis and Kernel DCA are effective and promising in learning good quality distance metrics for image retrieval.
View on IEEE
Deep Learning for Person Re-Identification: A Survey and Outlook
TLDR
A powerful AGW baseline is designed, achieving state-of-the-art or at least comparable performance on twelve datasets for four different Re-ID tasks, and a new evaluation metric (mINP) is introduced, indicating the cost for finding all the correct matches, which provides an additional criteria to evaluate the Re- ID system for real applications.
View on IEEE
Batch mode active learning and its application to medical image classification
TLDR
A framework for "batch mode active learning" that applies the Fisher information matrix to select a number of informative examples simultaneously and is more effective than the state-of-the-art algorithms for active learning.
View on ACM
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License