Search Results for author:
Found 33 papers, 8 papers with code
Mutual-Learning Improves End-to-End Speech Translation
In this paper, we propose an alternative–a trainable mutual-learning scenario, where the MT and the ST models are collaboratively trained and are considered as peers, rather than teacher/student.
Neural Image Compression with Quantization Rectifier
This paper presents a novel quantization rectifier (QR) method for image compression that leverages image feature correlation to mitigate the impact of quantization.
MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline
Large language models (LLMs) have seen considerable advancements in natural language understanding tasks, yet there remains a gap to bridge before attaining true artificial general intelligence, especially concerning shortcomings in mathematical reasoning capabilities.
Pre-trained Large Language Models for Financial Sentiment Analysis
Financial sentiment analysis refers to classifying financial text contents into sentiment categories (e. g. positive, negative, and neutral).
Powerformer: A Section-adaptive Transformer for Power Flow Adjustment
In this paper, we present a novel transformer architecture tailored for learning robust power system state representations, which strives to optimize power dispatch for the power flow adjustment across different transmission sections.
DTP-Net: Learning to Reconstruct EEG signals in Time-Frequency Domain by Multi-scale Feature Reuse
Finally, a Decoder layer is employed to reconstruct the artifact-reduced EEG signal.
Adaptive Policy with Wait-$k$ Model for Simultaneous Translation
Simultaneous machine translation (SiMT) requires a robust read/write policy in conjunction with a high-quality translation model.
Dual Effects of the US-China Trade War and COVID-19 on United States Imports: Transfer of China's industrial chain?
However, the worldwide lockdowns over pandemic have reversed this trend as, over this period, the U. S. effectively imported more goods directly from China and indirectly through Southeast Asian exporters that imported from China.
Do We Need an Encoder-Decoder to Model Dynamical Systems on Networks?
As deep learning gains popularity in modelling dynamical systems, we expose an underappreciated misunderstanding relevant to modelling dynamics on networks.
Visual Anomaly Detection via Dual-Attention Transformer and Discriminative Flow
In this paper, we introduce the novel state-of-the-art Dual-attention Transformer and Discriminative Flow (DADF) framework for visual anomaly detection.
Ranked #14 on
Anomaly Detection
on MVTec LOCO AD
One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization
To alleviate the potentially catastrophic forgetting issue in multilingual models, we fix all pre-trained model parameters, insert the parameter-efficient structure adapter, and fine-tune it.
Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection
To address this issue, we propose a two-branch approach that consists of a local branch for detecting structural anomalies and a global branch for detecting logical anomalies.
Ranked #16 on
Anomaly Detection
on MVTec LOCO AD
CyberLoc: Towards Accurate Long-term Visual Localization
Second, a single-image-based localization pipeline (retrieval--matching--PnP) is performed to estimate 6-DoF camera poses for each query image, one for each 3D map.
Normal Reference Attention and Defective Feature Perception Network for Surface Defect Detection
Unlike most reconstruction-based methods, our NDP-Net first employs an encoding module that extracts multi scale discriminative features of the surface textures, which is augmented with the defect discriminative ability by the proposed artificial defects and the novel pixel-level defect perception loss.
Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation
Existing zero-shot methods fail to align the two modalities of speech and text into a shared semantic space, resulting in much worse performance compared to the supervised ST methods.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Clear Memory-Augmented Auto-Encoder for Surface Defect Detection
At first, we propose a novel clear memory-augmented module (CMAM), which combines the encoding and memoryencoding in a way of forgetting and inputting, thereby repairing abnormal foregrounds and preserving clear backgrounds.
Feature Transformation for Cross-domain Few-shot Remote Sensing Scene Classification
Moreover, FTM can be effectively learned on target domain in the case of few training data available and is agnostic to specific network structures.
Robust Neural Regression via Uncertainty Learning
Deep neural networks tend to underestimate uncertainty and produce overly confident predictions.
Distributed Optimization of Graph Convolutional Network using Subgraph Variance
We first propose a graph augmentation-based partition (GAD-Partition) that can divide original graph into augmented subgraphs to reduce communication by selecting and storing as few significant nodes of other processors as possible while guaranteeing the accuracy of the training.
Product-oriented Machine Translation with Cross-modal Cross-lingual Pre-training
Firstly, there are many specialized jargons in the product description, which are ambiguous to translate without the product image.
About lifespan and the continuous dependence for the Navier-Stokes equation in $\dot{B}^{\frac{d}{p}-1}_{p,r}$
Combining \cite{wbx, ns7, ns2}, we deduce that $\dot{B}^{\frac{d}{p}-1}_{p,\infty}$ with $1\leq p<\infty$ is the critical space which solutions are ill-posedness, while $u\in\dot{B}^{\frac{d}{p}-1}_{p, r}$ with $1\leq r, p<\infty$ are well-poseness.
Analysis of PDEs
MODEL: Motif-based Deep Feature Learning for Link Prediction
Link prediction plays an important role in network analysis and applications.
Learning Semantically Enhanced Feature for Fine-Grained Image Classification
We aim to provide a computationally cheap yet effective approach for fine-grained image classification (FGIC) in this letter.
Ranked #14 on
Fine-Grained Image Classification
on Stanford Dogs
Cross-X Learning for Fine-Grained Visual Categorization
Recognizing objects from subcategories with very subtle differences remains a challenging task due to the large intra-class and small inter-class variation.
Ranked #18 on
Fine-Grained Image Classification
on NABirds
(using extra training data)
Fine-Grained Image Classification
Fine-Grained Visual Categorization
Aligning Linguistic Words and Visual Semantic Units for Image Captioning
Image captioning attempts to generate a sentence composed of several linguistic words, which are used to describe objects, attributes, and interactions in an image, denoted as visual semantic units in this paper.
Learning Longer-term Dependencies via Grouped Distributor Unit
Learning long-term dependencies still remains difficult for recurrent neural networks (RNNs) despite their success in sequence modeling recently.
IRCMS at SemEval-2018 Task 7 : Evaluating a basic CNN Method and Traditional Pipeline Method for Relation Classification
We experimented on this task with two methods: CNN method and traditional pipeline method.
Inverse Moment Methods for Sufficient Forecasting using High-Dimensional Predictors
Assuming that the predictors affect the response through the latent factors, we propose to first conduct factor analysis and then apply sufficient dimension reduction on the estimated factors, to derive the reduced data for subsequent forecasting.
Control Matching via Discharge Code Sequences
In this paper, we consider the patient similarity matching problem over a cancer cohort of more than 220, 000 patients.
Preterm Birth Prediction: Deriving Stable and Interpretable Rules from High Dimensional Data
Preterm births occur at an alarming rate of 10-15%.
adaptive direction information in differential evolution for numerical optimization
In most of the DE algorithms, the neighborhood and direction information are not fully and simultaneously exploited to guide the search.
Unsupervised Pretraining Encourages Moderate-Sparseness
It is well known that direct training of deep neural networks will generally lead to poor results.
