Search Results for author:
Found 22 papers, 11 papers with code
Robust Computer Vision in an Ever-Changing World: A Survey of Techniques for Tackling Distribution Shifts
As a result, it raises concerns about the overall robustness of the machine learning techniques for computer vision applications that are deployed publicly for consumers.
Deep Feature Registration for Unsupervised Domain Adaptation
While unsupervised domain adaptation has been explored to leverage the knowledge from a labeled source domain to an unlabeled target domain, existing methods focus on the distribution alignment between two domains.
Unconfounded Propensity Estimation for Unbiased Ranking
The goal of unbiased learning to rank (ULTR) is to leverage implicit user feedback for optimizing learning-to-rank systems.
Model-based Unbiased Learning to Rank
Existing methods in unbiased learning to rank typically rely on click modeling or inverse propensity weighting (IPW).
StruBERT: Structure-aware BERT for Table Search and Matching
In this paper, we propose StruBERT, a structure-aware BERT model that fuses the textual and structural information of a data table to produce context-aware representations for both textual and tabular content of a data table.
Memory Defense: More Robust Classification via a Memory-Masking Autoencoder
Ideally, a robust classifier would be immune to small variations in input images, and a number of defensive approaches have been created as a result.
Deep Least Squares Alignment for Unsupervised Domain Adaptation
Unsupervised domain adaptation leverages rich information from a labeled source domain to model an unlabeled target domain.
Automatic Head Overcoat Thickness Measure with NASNet-Large-Decoder Net
To further improve segmentation results, we are the first to propose a post-processing layer to remove irrelevant portions in the segmentation result.
Enhanced Separable Disentanglement for Unsupervised Domain Adaptation
The reconstructed features are also not sufficiently used during training.
Correlated Adversarial Joint Discrepancy Adaptation Network
To address these issues, we propose a novel approach called correlated adversarial joint discrepancy adaptation network (CAJNet), which minimizes the joint discrepancy of two domains and achieves competitive performance with tuning parameters using the correlated label.
Deep Spherical Manifold Gaussian Kernel for Unsupervised Domain Adaptation
To align the conditional distributions, we further develop an easy-to-hard pseudo label refinement process to improve the quality of the pseudo labels and then reduce categorical spherical manifold Gaussian kernel geodesic loss.
WTR: A Test Collection for Web Table Retrieval
We describe the development, characteristics and availability of a test collection for the task of Web table retrieval, which uses a large-scale Web Table Corpora extracted from the Common Crawl.
Efficient Pre-trained Features and Recurrent Pseudo-Labeling in Unsupervised Domain Adaptation
In this paper, we show how to efficiently opt for the best pre-trained features from seventeen well-known ImageNet models in unsupervised DA problems.
Adversarial Regression Learning for Bone Age Estimation
In this paper, we propose an adversarial regression learning network (ARLNet) for bone age estimation.
Neural ranking models for document retrieval
A variety of deep learning models have been proposed, and each model presents a set of neural network components to extract features that are used for ranking.
Adversarial Consistent Learning on Partial Domain Adaptation of PlantCLEF 2020 Challenge
Adversarial learning loss can maintain domain-invariant features between the source and target domains.
Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification
Extreme multi-label text classification (XMTC) is a task for tagging a given text with the most relevant labels from an extremely large label set.
Table Search Using a Deep Contextualized Language Model
Pretrained contextualized language models such as BERT have achieved impressive results on various natural language processing benchmarks.
Impact of ImageNet Model Selection on Domain Adaptation
We extract features from sixteen distinct pre-trained ImageNet models and examine the performance of twelve benchmarking methods when using the features.
Leveraging Schema Labels to Enhance Dataset Search
We incorporate the generated schema labels into a mixed ranking model which not only considers the relevance between the query and dataset metadata but also the similarity between the query and generated schema labels.
Modified Distribution Alignment for Domain Adaptation with Pre-trained Inception ResNet
Deep neural networks have been widely used in computer vision.
Ranked #14 on
Domain Adaptation
on Office-31
IP Geolocation through Reverse DNS
We propose a systematic approach to use publicly accessible reverse DNS hostnames for geolocating IP addresses.
