Search Results for author:
Found 50 papers, 16 papers with code
Translation Quality Estimation by Jointly Learning to Score and Rank
In order to make use of different types of human evaluation data for supervised learning, we present a multi-task learning QE model that jointly learns two tasks: score a translation and rank two translations.
NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results
This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results.
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking.
Learning Expressive And Generalizable Motion Features For Face Forgery Detection
However, current sequence-based face forgery detection methods use general video classification networks directly, which discard the special and discriminative motion information for face manipulation detection.
Diving Deep into Regions: Exploiting Regional Information Transformer for Single Image Deraining
Our RTB is used for attention selection of rain-affected and unaffected regions and local modeling of mixed scales.
Learning to Prompt Segment Anything Models
SAMs work with two types of prompts including spatial prompts (e. g., points) and semantic prompts (e. g., texts), which work together to prompt SAMs to segment anything on downstream datasets.
Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey
Traditional computer vision generally solves each single task independently by a dedicated model with the task instruction implicitly designed in the model architecture, arising two limitations: (1) it leads to task-specific models, which require multiple models for different tasks and restrict the potential synergies from diverse tasks; (2) it leads to a pre-defined and fixed model interface that has limited interactivity and adaptability in following user' task instructions.
Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memory
However, the source predictions of target data are often noisy and training with them is prone to learning collapses.
Prompt Ensemble Self-training for Open-Vocabulary Domain Adaptation
Traditional domain adaptation assumes the same vocabulary across source and target domains, which often struggles with limited transfer flexibility and efficiency while handling target domains with different vocabularies.
Exploring Paracrawl for Document-level Neural Machine Translation
We show that document-level NMT models trained with only parallel paragraphs from Paracrawl can be used to translate real documents from TED, News and Europarl, outperforming sentence-level NMT models.
Vision-Language Models for Vision Tasks: A Survey
Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks (DNNs) training, and they usually train a DNN for each single visual recognition task, leading to a laborious and time-consuming visual recognition paradigm.
Semantic-visual Guided Transformer for Few-shot Class-incremental Learning
And then, a text encoder is introduced to automatically generate the corresponding semantic (text) labels for each image from the base classes.
Ranked #1 on
Few-Shot Class-Incremental Learning
on CUB-200-2011
Indescribable Multi-modal Spatial Evaluator
IMSE creates an accurate multi-modal spatial evaluator to measure spatial differences between two images, and then optimizes registration by minimizing the error predicted of the evaluator.
PMT-IQA: Progressive Multi-task Learning for Blind Image Quality Assessment
To verify the effectiveness of the proposed PMT-IQA model, we conduct experiments on four widely used public datasets, and the experimental results indicate that the performance of PMT-IQA is superior to the comparison approaches, and both MS and PMT modules improve the model's performance.
Generalizable Black-Box Adversarial Attack with Meta Learning
In the scenario of black-box adversarial attack, the target model's parameters are unknown, and the attacker aims to find a successful adversarial perturbation based on query feedback under a query budget.
Domain Adaptive Scene Text Detection via Subcategorization
We study domain adaptive scene text detection, a largely neglected yet very meaningful task that aims for optimal transfer of labelled scene text images while handling unlabelled images in various new domains.
CPS Attack Detection under Limited Local Information in Cyber Security: A Multi-node Multi-class Classification Ensemble Approach
In order to train a global multi-class classifier without sharing the raw data across all nodes, the main result of our study is designing a multi-node multi-class classification ensemble approach.
Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors
Multi-scale features have been proven highly effective for object detection but often come with huge and even prohibitive extra computation costs, especially for the recent Transformer-based detectors.
Automating DBSCAN via Deep Reinforcement Learning
DBSCAN is widely used in many scientific and engineering fields because of its simplicity and practicality.
Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution
On the other hand, we propose a parallel network which includes two branches of cascaded lookup tables which process different components of the input low-resolution images.
UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration
Domain adaptive panoptic segmentation aims to mitigate data annotation challenge by leveraging off-the-shelf annotated data in one or multiple related source domains.
Ranked #2 on
Domain Adaptation
on Panoptic SYNTHIA-to-Cityscapes
An optimal transport approach for selecting a representative subsample with application in efficient kernel density estimation
Theoretically, we show the selected subsample can be used for efficient density estimation by deriving the convergence rate for the proposed subsample kernel density estimator.
LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Clouds
Quantitative and qualitative experiments show that our method outperforms the techniques based only on RGB images.
Ranked #3 on
3D Human Pose Estimation
on SLOPER4D
(using extra training data)
Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks
Despite the usefulness of this service, we consider that recommending courses to users directly may neglect their varying degrees of expertise.
A Bidirectional Transformer Based Alignment Model for Unsupervised Word Alignment
We further fine-tune the target-to-source attention in the BTBA model to obtain better alignments using a full context based optimization method and self-supervised training.
Oversampling Divide-and-conquer for Response-skewed Kernel Ridge Regression
The divide-and-conquer method has been widely used for estimating large-scale kernel ridge regression estimates.
Spectral Unsupervised Domain Adaptation for Visual Recognition
Second, it introduces multi-view spectral learning that learns useful unsupervised representations by maximizing mutual information among multiple ST-generated spectral views of each target sample.
Large-scale optimal transport map estimation using projection pursuit
We theoretically show the proposed dimension reduction method can consistently estimate the most ``informative'' projection direction in each iteration.
Ensemble machine learning approach for screening of coronary heart disease based on echocardiography and risk factors
Background: Extensive clinical evidence suggests that a preventive screening of coronary heart disease (CHD) at an earlier stage can greatly reduce the mortality rate.
Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks
To avoid the embedding over-assimilation among different types of nodes, we employ a label-aware neural similarity measure to ascertain the most similar neighbors based on node attributes.
Ranked #3 on
Node Classification
on Amazon-Fraud
A Detector-oblivious Multi-arm Network for Keypoint Matching
This paper presents a matching network to establish point correspondence between images.
DA-DETR: Domain Adaptive Detection Transformer with Information Fusion
DA-DETR introduces a novel CNN-Transformer Blender (CTBlender) that fuses the CNN features and Transformer features ingeniously for effective feature alignment and knowledge transfer across domains.
Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation
The ambiguity naturally leads to the issue of \emph{implicit multi-label}, motivating the need for diverse predictions.
Self-Domain Adaptation for Face Anti-Spoofing
In this paper, we propose a self-domain adaptation framework to leverage the unlabeled test domain data at inference.
Dual ResGCN for Balanced Scene GraphGeneration
We propose to incorporate the prior about the co-occurrence of relation pairs into the graph to further help alleviate the class imbalance issue.
Sufficient dimension reduction for classification using principal optimal transport direction
The proposed method, named principal optimal transport direction (POTD), estimates the basis of the SDR subspace using the principal directions of the optimal transport coupling between the data respecting different response categories.
A Review on Modern Computational Optimal Transport Methods with Applications in Biomedical Research
Optimal transport has been one of the most exciting subjects in mathematics, starting from the 18th century.
Learning Source Phrase Representations for Neural Machine Translation
Considering that modeling phrases instead of words has significantly improved the Statistical Machine Translation (SMT) approach through the use of larger translation blocks ("phrases") and its reordering ability, modeling NMT at phrase level is an intuitive proposal to help the model capture long-distance relationships.
Lipschitz Constrained Parameter Initialization for Deep Transformers
In this paper, we first empirically demonstrate that a simple modification made in the official implementation, which changes the computation order of residual connection and layer normalization, can significantly ease the optimization of deep Transformers.
DFKI-NMT Submission to the WMT19 News Translation Task
This paper describes the DFKI-NMT submission to the WMT19 News translation task.
Generative Domain-Migration Hashing for Sketch-to-Image Retrieval
The generative model learns a mapping that the distributions of sketches can be indistinguishable from the distribution of natural images using an adversarial loss, and simultaneously learns an inverse mapping based on the cycle consistency loss in order to enhance the indistinguishability.
UniMa at SemEval-2018 Task 7: Semantic Relation Extraction and Classification from Scientific Publications
Large repositories of scientific literature call for the development of robust methods to extract information from scholarly papers.
Guiding Neural Machine Translation with Retrieved Translation Pieces
Specifically, for an input sentence, we use a search engine to retrieve sentence pairs whose source sides are similar with the input sentence, and then collect $n$-grams that are both in the retrieved target sentences and aligned with words that match in the source sentences, which we call "translation pieces".
Improving Neural Machine Translation through Phrase-based Forced Decoding
Compared to traditional statistical machine translation (SMT), neural machine translation (NMT) often sacrifices adequacy for the sake of fluency.
