Search Results for author:
Found 110 papers, 45 papers with code
The DeepMind Chinese–English Document Translation System at WMT2020
This paper describes the DeepMind submission to the Chinese\rightarrowEnglish constrained data track of the WMT2020 Shared Task on News Translation.
Non-Uniform Exposure Imaging via Neuromorphic Shutter Control
To address this challenge, we propose a novel Neuromorphic Shutter Control (NSC) system to avoid motion blurs and alleviate instant noises, where the extremely low latency of events is leveraged to monitor the real-time motion and facilitate the scene-adaptive exposure.
MTGA: Multi-view Temporal Granularity aligned Aggregation for Event-based Lip-reading
Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated.
Detecting Every Object from Events
Object detection is critical in autonomous driving, and it is more practical yet challenging to localize objects of unknown categories: an endeavour known as Class-Agnostic Object Detection (CAOD).
Inclusive Design Insights from a Preliminary Image-Based Conversational Search Systems Evaluation
The digital realm has witnessed the rise of various search modalities, among which the Image-Based Conversational Search System stands out.
Mechanisms of non-factual hallucinations in language models
Our study investigates the mechanistic causes of hallucination, specifically non-factual ones where the LM incorrectly predicts object attributes in response to subject-relation queries.
Using construction waste hauling trucks' GPS data to classify earthwork-related locations: A Chengdu case study
Earthwork-related locations (ERLs), such as construction sites, earth dumping ground, and concrete mixing stations, are major sources of urban dust pollution (particulate matters).
An LLM Maturity Model for Reliable and Transparent Text-to-Query
Recognizing the imperative to address the reliability and transparency issues of Large Language Models (LLM), this work proposes an LLM maturity model tailored for text-to-query applications.
Neuromorphic Synergy for Video Binarization
We also develop an efficient integration method to propagate this binary image to high frame rate binary video.
A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspective
Vertical Federated Learning (VFL) is a federated learning paradigm where multiple participants, who share the same set of samples but hold different features, jointly train machine learning models.
Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation
We investigate this approach under two different settings: one where the policy model is smaller and is paired with a more powerful critic model, and another where a single language model fulfills both roles.
Re-evaluating the Memory-balanced Pipeline Parallelism: BPipe
Pipeline parallelism is an essential technique in the training of large-scale Transformer models.
Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control
This paper proposes Imperio, which harnesses the language understanding capabilities of NLP models to enrich backdoor attacks.
RoleCraft-GLM: Advancing Personalized Role-Playing in Large Language Models
This study presents RoleCraft-GLM, an innovative framework aimed at enhancing personalized role-playing with Large Language Models (LLMs).
SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery
Prior studies on Remote Sensing Foundation Model (RSFM) reveal immense potential towards a generic model for Earth Observation.
Systematic word meta-sense extension
The meaning of polysemous words often varies in a highly productive yet predictable way.
CrossZoom: Simultaneously Motion Deblurring and Event Super-Resolving
Even though the collaboration between traditional and neuromorphic event cameras brings prosperity to frame-event based vision applications, the performance is still confined by the resolution gap crossing two modalities in both spatial and temporal domains.
Learning Parallax for Stereo Event-based Motion Deblurring
To tackle this problem, we propose a novel coarse-to-fine framework, named NETwork of Event-based motion Deblurring with STereo event and intensity cameras (St-EDNet), to recover high-quality images directly from the misaligned inputs, consisting of a single blurry image and the concurrent event streams.
Circle Feature Graphormer: Can Circle Features Stimulate Graph Transformer?
Firstly, we define the first circle feature as modified swing for common graph, which comes from bipartite graph.
Ranked #1 on
Link Property Prediction
on ogbl-citation2
LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning
In response to this research gap, we present LLaMA-Reviewer, an innovative framework that leverages the capabilities of LLaMA, a popular LLM, in the realm of code review.
Generalizing Event-Based Motion Deblurring in Real-World Scenarios
Event-based motion deblurring has shown promising results by exploiting low-latency events.
Video Frame Interpolation with Stereo Event and Intensity Camera
The stereo event-intensity camera setup is widely applied to leverage the advantages of both event cameras with low latency and intensity cameras that capture accurate brightness and texture information.
"Seeing'' Electric Network Frequency from Events
Most of the artificial lights fluctuate in response to the grid's alternating current and exhibit subtle variations in terms of both intensity and spectrum, providing the potential to estimate the Electric Network Frequency (ENF) from conventional frame-based videos.
Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection
Despite the exploration of adaptive label assignment in recent oriented object detectors, the extreme geometry shape and limited feature of oriented tiny objects still induce severe mismatch and imbalance issues.
Ranked #2 on
Oriented Object Detction
on DOTA 2.0
Self-Supervised Scene Dynamic Recovery from Rolling Shutter Images and Events
Scene Dynamic Recovery (SDR) by inverting distorted Rolling Shutter (RS) images to an undistorted high frame-rate Global Shutter (GS) video is a severely ill-posed problem due to the missing temporal dynamic information in both RS intra-frame scanlines and inter-frame exposures, particularly when prior knowledge about camera/object motions is unavailable.
DIPNet: Efficiency Distillation and Iterative Pruning for Image Super-Resolution
To address this issue, we propose a novel multi-stage lightweight network boosting method, which can enable lightweight networks to achieve outstanding performance.
Recovering Continuous Scene Dynamics from A Single Blurry Image with Events
This paper aims at demystifying a single motion-blurred image with events and revealing temporally continuous scene dynamics encrypted behind motion blurs.
Learning to Super-Resolve Blurry Images with Events
Super-Resolution from a single motion Blurred image (SRB) is a severely ill-posed problem due to the joint degradation of motion blurs and low spatial resolution.
A Reparameterized Discrete Diffusion Model for Text Generation
This work studies discrete diffusion probabilistic models with applications to natural language generation.
A Comparison of Decision Forest Inference Platforms from A Database Perspective
In addition, the relation-centric representation we proposed significantly improved netsDB's performance in handling large-scale models, while the model reuse optimization we proposed further improved netsDB's performance in handling small-scale datasets.
High-level semantic feature matters few-shot unsupervised domain adaptation
However, the goal of FS-UDA and FSL are relevant yet distinct, since FS-UDA aims to classify the samples in target domain rather than source domain.
"Seeing" Electric Network Frequency From Events
Most of the artificial lights fluctuate in response to the grid's alternating current and exhibit subtle variations in terms of both intensity and spectrum, providing the potential to estimate the Electric Network Frequency (ENF) from conventional frame-based videos.
A Natural Bias for Language Generation Models
After just a few hundred training updates, a standard probabilistic model for language generation has likely not yet learnt many semantic or syntactic rules of natural language, making it difficult to estimate the probability distribution over next tokens.
Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features
While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power.
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
GT-CausIn: a novel causal-based insight for traffic prediction
We then present a novel model named Graph Spatial-Temporal Network Based on Causal Insight (GT-CausIn), where prior learned causal information is integrated with graph diffusion layers and temporal convolutional network (TCN) layers.
Learning to See Through with Events
Although synthetic aperture imaging (SAI) can achieve the seeing-through effect by blurring out off-focus foreground occlusions while recovering in-focus occluded scenes from multi-view images, its performance is often deteriorated by dense occlusions and extreme lighting conditions.
Detecting Line Segments in Motion-blurred Images with Events
To robustly detect line segments over motion blurs, we propose to leverage the complementary information of images and events.
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report
While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints.
Fast Nearest Convolution for Real-Time Efficient Image Super-Resolution
The proposed nearest convolution has the same performance as the nearest upsampling but is much faster and more suitable for Android NNAPI.
Motion Robust High-Speed Light-Weighted Object Detection With Event Camera
In this work, we propose a motion robust and high-speed detection pipeline which better leverages the event data.
RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection
Then, instead of assigning samples with IoU or center sampling strategy, a new Receptive Field Distance (RFD) is proposed to directly measure the similarity between the Gaussian receptive field and ground truth.
MAD for Robust Reinforcement Learning in Machine Translation
We introduce a new distributed policy gradient algorithm and show that it outperforms existing reward-aware training procedures such as REINFORCE, minimum risk training (MRT) and proximal policy optimization (PPO) in terms of training stability and generalization performance when optimizing machine translation models.
Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark
Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels.
GLF-CR: SAR-Enhanced Cloud Removal with Global-Local Fusion
The challenge of the cloud removal task can be alleviated with the aid of Synthetic Aperture Radar (SAR) images that can penetrate cloud cover.
Ranked #2 on
Cloud Removal
on SEN12MS-CR
Noun2Verb: Probabilistic frame semantics for word class conversion
We present a formal framework, Noun2Verb, that simulates the production and comprehension of novel denominal verb usages by modeling shared knowledge of speaker and listener in semantic frames.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Learning to Extract Building Footprints from Off-Nadir Aerial Images
In this paper, we propose an offset vector learning scheme, which turns the building footprint extraction problem in off-nadir images into an instance-level joint prediction problem of the building roof and its corresponding "roof to footprint" offset vector.
BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment
To overcome the challenges in BurstSR, we propose a Burst Super-Resolution Transformer (BSRT), which can significantly improve the capability of extracting inter-frame information and reconstruction.
Ranked #1 on
Burst Image Super-Resolution
on BurstSR
Unifying Motion Deblurring and Frame Interpolation with Events
Slow shutter speed and long exposure time of frame-based cameras often cause visual blur and loss of inter-frame information, degenerating the overall quality of captured videos.
Autofocus for Event Cameras
Focus control (FC) is crucial for cameras to capture sharp images in challenging real-world scenarios.
Backpropagation through Time and Space: Learning Numerical Methods with Multi-Agent Reinforcement Learning
We introduce Backpropagation Through Time and Space (BPTTS), a method for training a recurrent spatio-temporal neural network, that is used in a homogeneous multi-agent reinforcement learning (MARL) setting to learn numerical methods for hyperbolic conservation laws.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Enabling arbitrary translation objectives with Adaptive Tree Search
When applied to autoregressive models, our algorithm has different biases than beam search has, which enables a new analysis of the role of decoding bias in autoregressive models.
Deep Constrained Least Squares for Blind Image Super-Resolution
In this paper, we tackle the problem of blind image super-resolution(SR) with a reformulated degradation model and two novel modules.
Ranked #1 on
Blind Super-Resolution
on DIV2KRK - 2x upscaling
Synthetic Aperture Imaging With Events and Frames
This paper addresses this problem by leveraging the merits of both events and frames, leading to a fusion-based SAI (EF-SAI) that performs consistently under the different densities of occlusions.
A Normalized Gaussian Wasserstein Distance for Tiny Object Detection
Our key observation is that Intersection over Union (IoU) based metrics such as IoU itself and its extensions are very sensitive to the location deviation of the tiny objects, and drastically deteriorate the detection performance when used in anchor-based detectors.
Ranked #1 on
Object Detection
on AI-TOD
DRL-Clusters: Buffer Management with Clustering based Deep Reinforcement Learning
Buffer cache has been widely implemented in database systems to reduce disk I/Os.
Motion Deblurring with Real Events
In this paper, we propose an end-to-end learning framework for event-based motion deblurring in a self-supervised manner, where real-world events are exploited to alleviate the performance degradation caused by data inconsistency.
Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining
Natural language relies on a finite lexicon to express an unbounded set of emerging ideas.
EBSR: Feature Enhanced Burst Super-Resolution With Deformable Alignment
We propose a novel architecture to handle the problem of multi-frame super-resolution (MFSR).
Ranked #2 on
Burst Image Super-Resolution
on SyntheticBurst
Diverse Pretrained Context Encodings Improve Document Translation
We propose a new architecture for adapting a sentence-level sequence-to-sequence transformer by incorporating multiple pretrained document context signals and assess the impact on translation performance of (1) different pretraining approaches for generating these signals, (2) the quantity of parallel data for which document context is available, and (3) conditioning on source, target, or source and target contexts.
NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results
This paper reviews the NTIRE2021 challenge on burst super-resolution.
Pretraining the Noisy Channel Model for Task-Oriented Dialogue
Direct decoding for task-oriented dialogue is known to suffer from the explaining-away effect, manifested in models that prefer short and generic responses.
Ranked #2 on
End-To-End Dialogue Modelling
on MULTIWOZ 2.0
Event-based Synthetic Aperture Imaging with a Hybrid Network
Synthetic aperture imaging (SAI) is able to achieve the see through effect by blurring out the off-focus foreground occlusions and reconstructing the in-focus occluded targets from multi-view images.
ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras
Targeting at the unified line segment detection (ULSD) for both distorted and undistorted images, we propose to represent line segments with the Bezier curve model.
Ranked #5 on
Line Segment Detection
on wireframe dataset
(sAP10 metric)
Inferring symmetry in natural language
Our results show that a hybrid transfer learning model that integrates linguistic features with contextualized language models most faithfully predicts the empirical data.
Improving Spiking Sparse Recovery via Non-Convex Penalties
Compared with digital methods, sparse recovery based on spiking neural networks has great advantages like high computational efficiency and low power-consumption.
Mixed Noise Removal with Pareto Prior
To address this problem, we exploit the Pareto distribution as the priori of the weighting matrix, based on which an accurate and robust weight estimator is proposed for mixed noise removal.
Structure-Aware Network for Lane Marker Extraction with Dynamic Vision Sensor
We then propose a structure-aware network for lane marker extraction in DVS images.
Event Enhanced High-Quality Image Recovery
To recover high-quality intensity images, one should address both denoising and super-resolution problems for event cameras.
Implicit Euler ODE Networks for Single-Image Dehazing
Deep convolutional neural networks (CNN) have been applied for image dehazing tasks, where the residual network (ResNet) is often adopted as the basic component to avoid the vanishing gradient problem.
Kernel Learning for High-Resolution Time-Frequency Distribution
To break the current limitation, we propose a data-driven kernel learning model directly based on Wigner-Ville distribution (WVD).
IsarStep: a Benchmark for High-level Mathematical Reasoning
In this paper, we present a benchmark for high-level mathematical reasoning and study the reasoning capabilities of neural sequence-to-sequence models.
Robust Time-Frequency Reconstruction by Learning Structured Sparsity
Time-frequency distributions (TFDs) play a vital role in providing descriptive analysis of non-stationary signals involved in realistic scenarios.
Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks
We study multi-turn response generation for open-domain dialogues.
Capturing document context inside sentence-level neural machine translation models with self-training
Neural machine translation (NMT) has arguably achieved human level parity when trained and evaluated at the sentence-level.
Matching Neuromorphic Events and Color Images via Adversarial Learning
The event camera has appealing properties: high dynamic range, low latency, low power consumption and low memory usage, and thus provides complementariness to conventional frame-based cameras.
Edge-Isoperimetric Inequalities and Ball-Noise Stability: Linear Programming and Probabilistic Approaches
Our bounds derived by the second approach are expressed in terms of the \emph{noise stability}, and they are shown to be asymptotically tight as $n\to\infty$ when $r=2\lfloor\frac{\beta n}{2}\rfloor+1$ and $M=\lfloor\alpha2^{n}\rfloor$ for fixed $\alpha,\beta\in(0, 1)$, and is tight up to a factor $2$ when $r=2\lfloor\frac{\beta n}{2}\rfloor$ and $M=\lfloor\alpha2^{n}\rfloor$.
Combinatorics Information Theory Information Theory Probability
Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability
Second, through MPLens, we highlight how the vulnerability of pre-trained models under membership inference attack is not uniform across all classes, particularly when the training data itself is skewed.
Maximum Entropy Diverse Exploration: Disentangling Maximum Entropy Reinforcement Learning
A theoretical investigation shows that the set of policies learned by MEDE capture the same modalities as the optimal maximum entropy policy.
A Mutual Information Maximization Perspective of Language Representation Learning
We show state-of-the-art word representation learning methods maximize an objective function that is a lower bound on the mutual information between different parts of a word sequence (i. e., a sentence).
Learning Cluster Structured Sparsity by Reweighting
Recently, the paradigm of unfolding iterative algorithms into finite-length feed-forward neural networks has achieved a great success in the area of sparse recovery.
Better Document-Level Machine Translation with Bayes' Rule
We show that Bayes' rule provides an effective mechanism for creating document translation models that can be learned from only parallel sentences and monolingual documents---a compelling benefit as parallel documents are not always available.
Putting Machine Translation in Context with the Noisy Channel Model
We show that Bayes' rule provides a compelling mechanism for controlling unconditional document language models, using the long-standing challenge of effectively leveraging document context in machine translation.
Relative Pixel Prediction For Autoregressive Image Generation
In natural images, transitions between adjacent pixels tend to be smooth and gradual, a fact that has long been exploited in image compression models based on predictive coding.
Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks
Learning Rate (LR) is an important hyper-parameter to tune for effective training of deep neural networks (DNNs).
CRNet: Image Super-Resolution Using A Convolutional Sparse Coding Inspired Network
Convolutional Sparse Coding (CSC) has been attracting more and more attention in recent years, for making full use of image global correlation to improve performance on various computer vision applications.
Deep learning scheme for recovery of broadband microwave photonic receiving systems in transceivers without expert knowledge and system priors
However, the quality of the signals may be degraded by defective photonic analog links, especially in a complicated MWP system.
Facial Feature Embedded CycleGAN for VIS-NIR Translation
VIS-NIR face recognition remains a challenging task due to the distinction between spectral components of two modalities and insufficient paired training data.
Intra-Ensemble in Neural Networks
In this work, we propose Intra-Ensemble, an end-to-end ensemble strategy with stochastic channel recombination operations to train several sub-networks simultaneously within one neural network.
Unsupervised Recurrent Neural Network Grammars
On language modeling, unsupervised RNNGs perform as well their supervised counterparts on benchmarks in English and Chinese.
Ranked #8 on
Constituency Grammar Induction
on PTB Diagnostic ECG Database
(Max F1 (WSJ) metric)
Differentially Private Model Publishing for Deep Learning
However, when the training datasets are crowdsourced from individuals and contain sensitive information, the model parameters may encode private information and bear the risks of privacy leakage.
Diverse Exploration via Conjugate Policies for Policy Gradient Methods
We address the challenge of effective exploration while maintaining good performance in policy gradient methods.
Learning and Evaluating General Linguistic Intelligence
We define general linguistic intelligence as the ability to reuse previously acquired knowledge about a language's lexicon, syntax, semantics, and pragmatic conventions to adapt to new tasks quickly.
Variational Smoothing in Recurrent Neural Network Language Models
We present a new theoretical perspective of data noising in recurrent neural network language models (Xie et al., 2017).
Image Super-Resolution via RL-CSC: When Residual Learning Meets Convolutional Sparse Coding
We extend LISTA to its convolutional version and build the main part of our model by strictly following the convolutional form, which improves the network's interpretability.
Ranked #33 on
Image Super-Resolution
on BSD100 - 4x upscaling
Sentence Encoding with Tree-constrained Relation Networks
The meaning of a sentence is a function of the relations that hold between its words.
Tackling Sequence to Sequence Mapping Problems with Neural Networks
In Natural Language Processing (NLP), it is important to detect the relationship between two sequences or to generate a sequence of tokens given another observed sequence.
Adversarial Examples in Deep Learning: Characterization and Divergence
The burgeoning success of deep learning has raised the security and privacy concerns as more and more tasks are accompanied with sensitive data.
Towards Demystifying Membership Inference Attacks
Our empirical results additionally show that (1) using the type of target model under attack within the attack model may not increase attack effectiveness and (2) collaborative learning in federated systems exposes vulnerabilities to membership inference risks when the adversary is a participant in the federation.
Cryptography and Security
Diverse Exploration for Fast and Safe Policy Improvement
We study an important yet under-addressed problem of quickly and safely improving policies in online reinforcement learning domains.
Automatic Streaming Segmentation of Stereo Video Using Bilateral Space
In this paper, we take advantage of binocular camera and propose an unsupervised algorithm based on semi-supervised segmentation algorithm and extracting foreground part efficiently.
The Neural Noisy Channel
We formulate sequence to sequence transduction as a noisy channel decoding problem and use recurrent neural networks to parameterise the source and channel models.
Online Segment to Segment Neural Transduction
We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read.
GPU-FV: Realtime Fisher Vector and Its Applications in Video Monitoring
We also applied GPU-FV for realtime video monitoring tasks and found that GPU-FV outperforms a number of previous works.
Neural Variational Inference for Text Processing
We validate this framework on two very different text modelling applications, generative document modelling and supervised question answering.
Ranked #1 on
Question Answering
on QASent
The SYSU System for the Interspeech 2015 Automatic Speaker Verification Spoofing and Countermeasures Challenge
In order to detect these spoofed speech signals as a countermeasure, we propose a score level fusion approach with several different i-vector subsystems.
Small Instance Detection by Integer Programming on Object Density Maps
For each region, a sliding window (ROI) is passed over the density map to calculate the instance count within each ROI.
Deep Learning for Answer Sentence Selection
Answer sentence selection is the task of identifying sentences that contain the answer to a given question.
Ranked #3 on
Question Answering
on QASent
