Search Results for author:
Found 112 papers, 48 papers with code
Recurrent Attention for Neural Machine Translation
Across an extensive set of experiments on 10 machine translation tasks, we find that RAN models are competitive and outperform their Transformer counterpart in certain scenarios, with fewer parameters and inference time.
Tencent Neural Machine Translation Systems for the WMT20 News Translation Task
This paper describes Tencent Neural Machine Translation systems for the WMT 2020 news translation tasks.
Tencent Translation System for the WMT21 News Translation Task
Based on our success in the last WMT, we continuously employed advanced techniques such as large batch training, data selection and data filtering.
Learned Scanpaths Aid Blind Panoramic Video Quality Assessment
Panoramic videos have the advantage of providing an immersive and interactive viewing experience.
Modular Blind Video Quality Assessment
Blind video quality assessment (BVQA) plays a pivotal role in evaluating and improving the viewing experience of end-users across a wide range of video-based platforms and services.
PreDiff: Precipitation Nowcasting with Latent Diffusion Models
We conduct empirical studies on two datasets: N-body MNIST, a synthetic dataset with chaotic behavior, and SEVIR, a real-world precipitation nowcasting dataset.
Tailoring Instructions to Student's Learning Levels Boosts Knowledge Distillation
It has been commonly observed that a teacher model with superior performance does not necessarily result in a stronger student, highlighting a discrepancy between current teacher training practices and effective knowledge transfer.
XTab: Cross-table Pretraining for Tabular Transformers
The success of self-supervised learning in computer vision and natural language processing has motivated pretraining methods on tabular data.
Scanpath Prediction in Panoramic Videos via Expected Code Length Minimization
Predicting human scanpaths when exploring panoramic videos is a challenging task due to the spherical geometry and the multimodality of the input, and the inherent uncertainty and diversity of the output.
A Cheaper and Better Diffusion Language Model with Soft-Masked Noise
Diffusion models that are based on iterative denoising have been recently proposed and leveraged in various generation tasks like image generation.
Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition
This work proposes POMP, a prompt pre-training method for vision-language models.
RAF: Holistic Compilation for Deep Learning Model Training
In this paper, we present RAF, a deep learning compiler for training.
LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation
Layout-to-image generation refers to the task of synthesizing photo-realistic images based on semantic layouts.
AIM: Adapting Image Models for Efficient Video Action Recognition
Recent vision transformer based video models mostly follow the ``image pre-training then finetuning" paradigm and have achieved great success on multiple video benchmarks.
Ranked #3 on
Action Recognition
on Diving-48
(using extra training data)
Multimodal Chain-of-Thought Reasoning in Language Models
Experimental results on ScienceQA and A-OKVQA benchmark datasets show the effectiveness of our proposed approach.
Ranked #4 on
Science Question Answering
on ScienceQA
Parameter-Efficient Fine-Tuning Design Spaces
We discover the following design patterns: (i) group layers in a spindle pattern; (ii) allocate the number of trainable parameters to layers uniformly; (iii) tune all the groups; (iv) assign proper tuning strategies to different groups.
Learning Multimodal Data Augmentation in Feature Space
The ability to jointly learn from multiple modalities, such as text, audio, and visual data, is a defining feature of intelligent systems.
SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learning
Pre-trained large language models can efficiently interpolate human-written prompts in a natural way.
What Makes for Good Tokenizers in Vision Transformer?
The architecture of transformers, which recently witness booming applications in vision tasks, has pivoted against the widespread convolutional paradigm.
Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift
Multimodal image-text models have shown remarkable performance in the past few years.
Visual Prompt Tuning for Test-time Domain Adaptation
First, DePT plugs visual prompts into the vision Transformer and only tunes these source-initialized prompts during adaptation.
Ranked #6 on
Domain Adaptation
on VisDA2017
Automatic Chain of Thought Prompting in Large Language Models
Providing these steps for prompting demonstrations is called chain-of-thought (CoT) prompting.
An Efficient Coarse-to-Fine Facet-Aware Unsupervised Summarization Framework based on Semantic Blocks
To tackle this problem, in this paper, we proposed an efficient Coarse-to-Fine Facet-Aware Ranking (C2F-FAR) framework for unsupervised long document summarization, which is based on the semantic block.
Earthformer: Exploring Space-Time Transformers for Earth System Forecasting
With the explosive growth of the spatiotemporal Earth observation data in the past decade, data-driven models that apply Deep Learning (DL) are demonstrating impressive potential for various Earth system forecasting tasks.
Ranked #1 on
Earth Surface Forecasting
on EarthNet2021 OOD Track
Removing Batch Normalization Boosts Adversarial Training
In addition, NoFrost achieves a $23. 56\%$ adversarial robustness against PGD attack, which improves the $13. 57\%$ robustness in BN-based AT.
Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition
However, in real-world applications, it is common for the training sets to have long-tailed distributions.
MixGen: A New Multi-Modal Data Augmentation
Data augmentation is a necessity to enhance data efficiency in deep learning.
Perceptual Quality Assessment of Virtual Reality Videos in the Wild
Investigating how people perceive virtual reality (VR) videos in the wild (i. e., those captured by everyday users) is a crucial and challenging task in VR-related applications due to complex authentic distortions localized in space and time.
Modeling Multi-Granularity Hierarchical Features for Relation Extraction
In this paper, we propose a novel method to extract multi-granularity features based solely on the original input sentences.
BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training
Multiple datasets and open challenges for object detection have been introduced in recent years.
Ranked #1 on
Object Detection
on BigDetection val
Task-guided Disentangled Tuning for Pretrained Language Models
Pretrained language models (PLMs) trained on large-scale unlabeled corpus are typically fine-tuned on task-specific downstream datasets, which have produced state-of-the-art results on various NLP tasks.
Learning Confidence for Transformer-based Neural Machine Translation
Confidence estimation aims to quantify the confidence of the model prediction, providing an expectation of success.
Pseudocylindrical Convolutions for Learned Omnidirectional Image Compression
We first describe parametric pseudocylindrical representation as a generalization of common pseudocylindrical map projections.
Benchmarking Multimodal AutoML for Tabular Data with Text Fields
We consider the use of automated supervised learning systems for data tables that not only contain numeric/categorical columns, but one or more text fields as well.
Ranked #2 on
Binary Classification
on kickstarter
Blending Anti-Aliasing into Vision Transformer
In this work, we analyze the uncharted problem of aliasing in vision transformer and explore to incorporate anti-aliasing properties.
Distiller: A Systematic Study of Model Distillation Methods in Natural Language Processing
We aim to identify how different components in the KD pipeline affect the resulting performance and how much the optimal KD pipeline varies across different datasets/tasks, such as the data augmentation policy, the loss function, and the intermediate representation for transferring the knowledge between teacher and student.
Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global Context
In terms of the local view, we first build a graph structure based on the document where phrases are regarded as vertices and the edges are similarities between vertices.
Progressive Coordinate Transforms for Monocular 3D Object Detection
Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment.
Video Contrastive Learning with Global Context
Our formulation is able to capture global context in a video, thus robust to temporal content change.
Attention Calibration for Transformer in Neural Machine Translation
Attention mechanisms have achieved substantial improvements in neural machine translation by dynamically selecting relevant inputs for different predictions.
A Unified Efficient Pyramid Transformer for Semantic Segmentation
Semantic segmentation is a challenging problem due to difficulties in modeling context in complex scenes and class confusions along boundaries.
Dive into Deep Learning
This open-source book represents our attempt to make deep learning approachable, teaching readers the concepts, the context, and the code.
Multimodal AutoML on Structured Tables with Text Fields
We design automated supervised learning systems for data tables that not only contain numeric/categorical columns, but text fields as well.
CrossNorm and SelfNorm for Generalization under Distribution Shifts
Can we develop new normalization methods to improve generalization robustness under distribution shifts?
Unity of Opposites: SelfNorm and CrossNorm for Model Robustness
CrossNorm exchanges styles between feature channels to perform style augmentation, diversifying the content and style mixtures.
A Comprehensive Study of Deep Video Action Recognition
Video action recognition is one of the representative tasks for video understanding.
Emotion Classification by Jointly Learning to Lexiconize and Classify
Emotion lexicons have been shown effective for emotion classification (Baziotis et al., 2018).
Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning
In addition, by transferring knowledge from other kinds of MRC tasks, our model achieves a new state-of-the-art results in both single and ensemble settings.
Ranked #1 on
Reading Comprehension
on RACE
FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems
FeatGraph provides a flexible programming interface to express diverse GNN models by composing coarse-grained sparse templates with fine-grained user-defined functions (UDFs) on each vertex/edge.
CSER: Communication-efficient SGD with Error Reset
The scalability of Distributed Stochastic Gradient Descent (SGD) is today limited by communication bottlenecks.
Accelerated Large Batch Optimization of BERT Pretraining in 54 minutes
Using the proposed LANS method and the learning rate scheme, we scaled up the mini-batch sizes to 96K and 33K in phases 1 and 2 of BERT pretraining, respectively.
Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference
Modern deep neural networks increasingly make use of features such as dynamic control flow, data structures and dynamic tensor shapes.
Machine learning formation enthalpies of intermetallics
The model uses easily accessible elemental properties as descriptors and has a mean absolute error (MAE) of 0. 025 eV/atom in predicting the formation enthalpy of stable binary intermetallics reported in the Materials Project database.
Materials Science
Learning Context-Based Non-local Entropy Modeling for Image Compression
To address this issue, we propose a non-local operation for context modeling by employing the global similarity within the context.
Improving Semantic Segmentation via Self-Training
In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models.
ResNeSt: Split-Attention Networks
It is well known that featuremap attention and multi-path representation are important for visual recognition.
Ranked #10 on
Instance Segmentation
on COCO test-dev
(APM metric)
AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data
We introduce AutoGluon-Tabular, an open-source AutoML framework that requires only a single line of Python to train highly accurate machine learning models on an unprocessed tabular dataset such as a CSV file.
Ranked #8 on
Molecular Property Prediction
on Tox21
GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing
We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating).
Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression
For the former, we directly apply a CCN to the binarized representation of an image to compute the Bernoulli distribution of each code for entropy estimation.
Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources
One difficulty we observe is that the noise in the stochastic momentum estimation is accumulated over time and will have delayed effects when the batch size changes.
Language Models with Transformers
In this paper, we explore effective Transformer architectures for language model, including adding additional LSTM layers to better capture the sequential context while still keeping the computation efficient.
Ranked #2 on
Language Modelling
on Penn Treebank (Word Level)
(using extra training data)
Learning Content-Weighted Deep Image Compression
Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance.
Bag of Freebies for Training Object Detection Neural Networks
Training heuristics greatly improve various image classification model accuracies~\cite{he2018bag}.
Bag of Tricks for Image Classification with Convolutional Neural Networks
Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods.
Ranked #38 on
Domain Generalization
on VizWiz-Classification
Bidirectional Generative Adversarial Networks for Neural Machine Translation
To address this issue and stabilize the GAN training, in this paper, we propose a novel Bidirectional Generative Adversarial Network for Neural Machine Translation (BGAN-NMT), which aims to introduce a generator model to act as the discriminator, whereby the discriminator naturally considers the entire translation space so that the inadequate training problem can be alleviated.
Approximate Distribution Matching for Sequence-to-Sequence Learning
Then, we interpret sequence-to-sequence learning as learning a transductive model to transform the source local latent distributions to match their corresponding target distributions.
Style Transfer as Unsupervised Machine Translation
Language style transferring rephrases text with specific stylistic attributes while preserving the original attribute-independent content.
Ranked #3 on
Unsupervised Text Style Transfer
on GYAFC
Regularizing Neural Machine Translation by Target-bidirectional Agreement
Although Neural Machine Translation (NMT) has achieved remarkable progress in the past several years, most NMT systems still suffer from a fundamental shortcoming as in other sequence generation tasks: errors made early in generation process are fed as inputs to the model and can be quickly amplified, harming subsequent sequence generation.
Generative Bridging Network for Neural Sequence Prediction
In order to alleviate data sparsity and overfitting problems in maximum likelihood estimation (MLE) for sequence prediction tasks, we propose the Generative Bridging Network (GBN), in which a novel bridge module is introduced to assist the training of the sequence prediction model (the generator network).
Triangular Architecture for Rare Language Translation
Neural Machine Translation (NMT) performs poor on the low-resource language pair $(X, Z)$, especially when $Z$ is a rare language.
Achieving Human Parity on Automatic Chinese to English News Translation
Machine translation has made rapid advances in recent years.
Ranked #3 on
Machine Translation
on WMT 2017 English-Chinese
Joint Training for Neural Machine Translation Models with Monolingual Data
Monolingual data have been demonstrated to be helpful in improving translation quality of both statistical machine translation (SMT) systems and neural machine translation (NMT) systems, especially in resource-poor or domain adaptation tasks where parallel data are not rich enough.
Shift-Net: Image Inpainting via Deep Feature Rearrangement
To this end, the encoder feature of the known region is shifted to serve as an estimation of the missing parts.
Enlarging Context with Low Cost: Efficient Arithmetic Coding with Trimmed Convolution
One key issue of arithmetic encoding method is to predict the probability of the current coding symbol from its context, i. e., the preceding encoded symbols, which usually can be executed by building a look-up table (LUT).
Stack-based Multi-layer Attention for Transition-based Dependency Parsing
Although sequence-to-sequence (seq2seq) network has achieved significant success in many NLP tasks such as machine translation and text summarization, simply applying this approach to transition-based dependency parsing cannot yield a comparable performance gain as in other state-of-the-art methods, such as stack-LSTM and head selection.
Sequence-to-Dependency Neural Machine Translation
Nowadays a typical Neural Machine Translation (NMT) model generates translations from left to right as a linear sequence, during which latent syntactic structures of the target sentences are not explicitly concerned.
Chunk-based Decoder for Neural Machine Translation
The chunk-level decoder models global dependencies while the word-level decoder decides the local word order in a chunk.
Generative Bridging Network in Neural Sequence Prediction
In order to alleviate data sparsity and overfitting problems in maximum likelihood estimation (MLE) for sequence prediction tasks, we propose the Generative Bridging Network (GBN), in which a novel bridge module is introduced to assist the training of the sequence prediction model (the generator network).
Learning Convolutional Networks for Content-weighted Image Compression
Therefore, the encoder, decoder, binarizer and importance map can be jointly optimized in an end-to-end manner by using a subset of the ImageNet database.
Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation
In neural machine translation, the attention mechanism facilitates the translation process by producing a soft alignment between the source sentence and the target sentence.
Deep Identity-aware Transfer of Facial Attributes
In general, our model consists of a mask network and an attribute transform network which work in synergy to generate a photo-realistic facial image with the reference attribute.
Ranked #2 on
Image-to-Image Translation
on RaFD
Convolutional Network for Attribute-driven and Identity-preserving Human Face Generation
Here we address this problem from the view of optimization, and suggest an optimization model to generate human face with the given attributes while keeping the identity of the reference image.
On the Powerball Method for Optimization
We propose a new method to accelerate the convergence of optimization algorithms.
Revise Saturated Activation Functions
In this paper, we revise two commonly used saturated functions, the logistic sigmoid and the hyperbolic tangent (tanh).
Data Driven Resource Allocation for Distributed Learning
In distributed machine learning, data is dispatched to multiple machines for processing.
MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
This paper describes both the API design and the system implementation of MXNet, and explains how embedding of both symbolic expression and tensor operation is handled in a unified fashion.
High Performance Latent Variable Models
Latent variable models have accumulated a considerable amount of interest from the industry and academia for their versatility in a wide range of applications.
AdaDelay: Delay Adaptive Distributed Stochastic Convex Optimization
We study distributed stochastic convex optimization under the delayed gradient model where the server nodes perform parameter updates, while the worker nodes compute stochastic gradients.
Graph Partitioning via Parallel Submodular Approximation to Accelerate Distributed Machine Learning
Distributed computing excels at processing large scale data, but the communication cost for synchronizing the shared parameters may slow down the overall performance.
Empirical Evaluation of Rectified Activations in Convolutional Network
In this paper we investigate the performance of different types of rectified activation functions in convolutional neural network: standard rectified linear unit (ReLU), leaky rectified linear unit (Leaky ReLU), parametric rectified linear unit (PReLU) and a new randomized leaky rectified linear units (RReLU).
Ranked #198 on
Image Classification
on CIFAR-100
Beyond Word-based Language Model in Statistical Machine Translation
Language model is one of the most important modules in statistical machine translation and currently the word-based language model dominants this community.
Communication Efficient Distributed Machine Learning with the Parameter Server
This paper describes a third-generation parameter server framework for distributed machine learning.
