Search Results for author:
Found 71 papers, 28 papers with code
PALM: Pre-training an Autoencoding\&Autoregressive Language Model for Context-conditioned Generation
An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks covering generative question answering (Rank 1 on the official MARCO leaderboard), abstractive summarization on CNN/DailyMail as well as Gigaword, question generation on SQuAD, and conversational response generation on Cornell Movie Dialogues.
Abstractive Text Summarization
Conversational Response Generation
+8
SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing images
These CD methods, however, still perform far from satisfactorily as we observe that 1) deep encoder layers focus on irrelevant background regions and 2) the models' confidence in the change regions is inconsistent at different decoder stages.
T-UNet: Triplet UNet for Change Detection in High-Resolution Remote Sensing Images
Siamese structure focuses on extracting object features at different times but lacks attention to change information, which leads to false alarms and missed detections.
DeepCL: Deep Change Feature Learning on Remote Sensing Images in the Metric Space
To address these issues, we complement the strong temporal modeling ability of metric learning with the prominent fitting ability of segmentation and propose a deep change feature learning (DeepCL) framework for robust and explainable CD.
Expediting Building Footprint Segmentation from High-resolution Remote Sensing Images via progressive lenient supervision
The efficacy of building footprint segmentation from remotely sensed images has been hindered by model transfer effectiveness.
Building-road Collaborative Extraction from Remotely Sensed Images via Cross-Interaction
Compared with many existing methods that train each task individually, the proposed collaborative extraction method can utilize the complementary advantages between buildings and roads by the proposed inter-task and inter-scale feature interactions, and automatically select the optimal reception field for different tasks.
Exploring Effective Priors and Efficient Models for Weakly-Supervised Change Detection
Specifically, change missing refer to the situation that the WSCD model fails to predict any changed pixels, even though the image-level label indicates changed, and vice versa for change fabricating.
Tiny-PPG: A Lightweight Deep Neural Network for Real-Time Detection of Motion Artifacts in Photoplethysmogram Signals on Edge Devices
Therefore, this study provides an effective solution for resource-constraint IoT smart health devices in PPG artifact detection.
GlobalMind: Global Multi-head Interactive Self-attention Network for Hyperspectral Change Detection
High spectral resolution imagery of the Earth's surface enables users to monitor changes over time in fine-grained scale, playing an increasingly important role in agriculture, defense, and emergency response.
EMS-Net: Efficient Multi-Temporal Self-Attention For Hyperspectral Change Detection
Hyperspectral change detection plays an essential role of monitoring the dynamic urban development and detecting precise fine object evolution and alteration.
Learning to Backdoor Federated Learning
In particular, we propose a general reinforcement learning-based backdoor attack framework where the attacker first trains a (non-myopic) attack policy using a simulator built upon its local data and common knowledge on the FL system, which is then applied during actual FL training.
HCGMNET: A Hierarchical Change Guiding Map Network For Change Detection
Very-high-resolution (VHR) remote sensing (RS) image change detection (CD) has been a challenging task for its very rich spatial information and sample imbalance problem.
Grafting Pre-trained Models for Multimodal Headline Generation
In this paper, we propose a novel approach to graft the video encoder from the pre-trained video-language model on the generative pre-trained language model.
Unsupervised Multimodal Change Detection Based on Structural Relationship Graph Representation Learning
Subsequently, the similarity levels of two structural relationships are calculated from learned graph representations and two difference images are generated based on the similarity levels.
Certified Robustness to Word Substitution Ranking Attack for Neural Ranking Models
A ranking model is said to be Certified Top-$K$ Robust on a ranked list when it is guaranteed to keep documents that are out of the top $K$ away from the top $K$ under any attack.
VLMAE: Vision-Language Masked Autoencoder
Image and language modeling is of crucial importance for vision-language pre-training (VLP), which aims to learn multi-modal representations from large-scale paired image-text data.
Exploiting Feature Diversity for Make-up Temporal Video Grounding
This technical report presents the 3rd winning solution for MTVG, a new task introduced in the 4-th Person in Context (PIC) Challenge at ACM MM 2022.
HyperNet: Self-Supervised Hyperspectral Spatial-Spectral Feature Understanding Network for Hyperspectral Change Detection
Only the positive samples at the same location of bi-temporal HSIs are created and forced to be aligned, aiming at learning the spectral difference-invariant features.
DeepPERF: A Deep Learning-Based Approach For Improving Software Performance
Additionally, we evaluate DeepPERF on 50 open source C# repositories on GitHub using both benchmark and unit tests and find that our model is able to suggest valid performance improvements that can improve both CPU usage and Memory allocations.
Multi-Temporal Spatial-Spectral Comparison Network for Hyperspectral Anomalous Change Detection
Hyperspectral anomalous change detection has been a challenging task for its emphasis on the dynamics of small and rare objects against the prevalent changes.
A heuristic method for data allocation and task scheduling on heterogeneous multiprocessor systems under memory constraints
Computing workflows in heterogeneous multiprocessor systems are frequently modeled as directed acyclic graphs of tasks and data blocks, which represent computational modules and their dependencies in the form of data produced by a task and used by others.
Learning from Drivers to Tackle the Amazon Last Mile Routing Research Challenge
On the one hand, our method encodes driver know-how by learning a sequential probability model from historical routes at the zone level, where each zone contains a few parcel stops.
Contrastive learning-based computational histopathology predict differential expression of cancer driver genes
We leveraged contrastive learning on large-scale unannotated WSIs to derive slide-level histopathological feature in latent space, and then transfer it to tumor diagnosis and prediction of differentially expressed cancer driver genes.
PRADA: Practical Black-Box Adversarial Attacks against Neural Ranking Models
We focus on the decision-based black-box attack setting, where the attackers cannot directly get access to the model information, but can only query the target model to obtain the rank positions of the partial retrieved list.
Programming Language Agnostic Mining of Code and Language Pairs with Sequence Labeling Based Question Answering
In particular, we propose to apply the BIO tagging scheme instead of the conventional binary scheme to mine the code solutions which are often composed of multiple blocks of a post.
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling
In the visual words learning module, we counter the first problem by enforcing the classification network to learn fine-grained visual word labels so that more object extents could be discovered.
Learning Deep Semantic Model for Code Search using CodeSearchNet Corpus
Different from typical information retrieval tasks, code search requires to bridge the semantic gap between the programming language and natural language, for better describing intrinsic concepts and semantics.
Dual-Tasks Siamese Transformer Framework for Building Damage Assessment
Considering the frontier advances of Transformer architecture in the computer vision field, in this paper, we present the first attempt at designing a Transformer-based damage assessment architecture (DamFormer).
Ranked #6 on
Extracting Buildings In Remote Sensing Images
on xBD
Disaster Response
Extracting Buildings In Remote Sensing Images
+1
Federated Unlearning with Knowledge Distillation
Federated Learning (FL) is designed to protect the data privacy of each client during the training process by transmitting only models instead of the original data.
Fully Convolutional Change Detection Framework with Generative Adversarial Network for Unsupervised, Weakly Supervised and Regional Supervised Change Detection
Deep learning for change detection is one of the current hot topics in the field of remote sensing.
Binary Change Guided Hyperspectral Multiclass Change Detection
In this study, we proposed an unsupervised Binary Change Guided hyperspectral multiclass change detection Network (BCG-Net) for HMCD, which aims at boosting the multiclass change detection result and unmixing result with the mature binary change detection approaches.
Exploring Forensic Dental Identification with Deep Learning
In this work, we pioneer to study deep learning for dental forensic identification based on panoramic radiographs.
LW-GCN: A Lightweight FPGA-based Graph Convolutional Network Accelerator
In this work, we propose LW-GCN, a lightweight FPGA-based accelerator with a software-hardware co-designed process to tackle irregularity in computation and memory access in GCN inference.
Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer
To this end, a semantic-edge domain adaptation architecture is proposed, which uses an independent edge stream to process edge information, thereby generating high-quality semantic boundaries over the target domain.
Ranked #32 on
Synthetic-to-Real Translation
on GTAV-to-Cityscapes Labels
(using extra training data)
Towards Deep and Efficient: A Deep Siamese Self-Attention Fully Efficient Convolutional Network for Change Detection in VHR Images
With the goal of designing a quite deep architecture to obtain more precise CD results while simultaneously decreasing parameter numbers to improve efficiency, in this work, we present a very deep and efficient CD network, entitled EffCDNet.
Are Neural Ranking Models Robust?
So we raise the question in this work: Are neural ranking models robust?
Distilling Transformers for Neural Cross-Domain Search
Pre-trained transformers have recently clinched top spots in the gamut of natural language tasks and pioneered solutions to software engineering tasks.
Tea: Program Repair Using Neural Network Based on Program Information Attention Matrix
The advance in machine learning (ML)-driven natural language process (NLP) points a promising direction for automatic bug fixing for software programs, as fixing a buggy program can be transformed to a translation task.
AKG: Automatic Kernel Generation for Neural Processing Units using Polyhedral Transformations
Existing tensor compilers have proven their effectiveness in deploying deep neural networks on general-purpose hardware like CPU and GPU, but optimizing for neural processing units (NPUs) is still challenging due to the heterogeneous compute units and complicated memory hierarchy.
Generating Bug-Fixes Using Pretrained Transformers
In this work we introduce DeepDebug: a data-driven program repair approach which learns to detect and fix bugs in Java methods mined from real-world GitHub repositories.
Generating Code with the Help of Retrieved Template Functions and Stack Overflow Answers
To demonstrate the effectiveness of our model designs, we perform extensive experiments with CodeSearchNet which contains template functions and CoNaLa which contains Stack Overflow intent-snippet pairs.
Transportation Density Reduction Caused by City Lockdowns Across the World during the COVID-19 Epidemic: From the View of High-resolution Remote Sensing Imagery
Considering that public transportation was mostly reduced or even forbidden, our results indicate that city lockdown policies are effective at limiting human transmission within cities.
Learning to Truncate Ranked Lists for Information Retrieval
One is the widely adopted metric such as F1 which acts as a balanced objective, and the other is the best F1 under some minimal recall constraint which represents a typical objective in professional search.
Mitigating Backdoor Attacks in Federated Learning
To minimize the pruning influence on test accuracy, we can fine-tune after pruning, and the attack success rate drops to 6. 4%, with only a 1. 7% loss of test accuracy.
Hyperspectral Anomaly Change Detection Based on Auto-encoder
In the ACDA model, two systematic auto-encoder (AE) networks are deployed to construct two predictors from two directions.
An Investigation of Traffic Density Changes inside Wuhan during the COVID-19 Epidemic with GF-2 Time-Series Images
The significant reduction and recovery of traffic density indicates that the lockdown policy in Wuhan show effectiveness in controlling human transmission inside the city, and the city returned to normal after lockdown lift.
DSDANet: Deep Siamese Domain Adaptation Convolutional Neural Network for Cross-domain Change Detection
By optimizing the network parameters and kernel coefficients with the source labeled data and target unlabeled data, DSDANet can learn transferrable feature representation that can bridge the discrepancy between two domains.
Multi-Temporal Scene Classification and Scene Change Detection with Correlation based Fusion
In this work, we proposed a CorrFusion module that fuses the highly correlated components in bi-temporal feature embeddings.
The GLEAM 4-Jy (G4Jy) Sample: II. Host-galaxy identification for individual sources
This is the GaLactic and Extragalactic All-sky MWA (GLEAM) Survey, and we have previously used a combination of visual inspection, cross-checks against the literature, and internal matching to identify the 'brightest' radio-sources ($S_{\mathrm{151MHz}} >$ 4 Jy) in the extragalactic catalogue (Galactic latitude, $|b| >$ 10 deg).
Astrophysics of Galaxies
The GLEAM 4-Jy (G4Jy) Sample: I. Definition and the catalogue
Of these G4Jy sources, 78 are resolved by the MWA (Phase-I) synthesised beam ($\sim$2 arcmin at 200 MHz), and we label 67% of the sample as 'single', 26% as 'double', 4% as 'triple', and 3% as having 'complex' morphology at $\sim$1 GHz (45-arcsec resolution).
Astrophysics of Galaxies
On the Encoder-Decoder Incompatibility in Variational Text Modeling and Beyond
To this end, we propose Coupled-VAE, which couples a VAE model with a deterministic autoencoder with the same structure and improves the encoder and decoder parameterizations via encoder weight sharing and decoder signal matching.
PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation
An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks covering generative question answering (Rank 1 on the official MARCO leaderboard), abstractive summarization on CNN/DailyMail as well as Gigaword, question generation on SQuAD, and conversational response generation on Cornell Movie Dialogues.
Ranked #1 on
Text Generation
on CNN/Daily Mail
Abstractive Text Summarization
Conversational Response Generation
+8
Deep Siamese Domain Adaptation Convolutional Neural Network for Cross-domain Change Detection in Multispectral Images
In this paper, we propose a novel deep siamese domain adaptation convolutional neural network (DSDANet) architecture for cross-domain change detection.
Unsupervised Change Detection in Multi-temporal VHR Images Based on Deep Kernel PCA Convolutional Mapping Network
Based on the KPCA convolution, an unsupervised deep siamese KPCA convolutional mapping network (KPCA-MNet) is designed for binary and multi-class change detection.
Symmetric Regularization based BERT for Pair-wise Semantic Reasoning
To remedy this, we propose to augment the NSP task to a 3-class categorization task, which includes a category for previous sentence prediction (PSP).
Incorporating External Knowledge into Machine Reading for Generative Question Answering
Different from existing work on knowledge-aware QA, we focus on a more challenging task of leveraging external knowledge to generate answers in natural language for a given question with context.
StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
Recently, the pre-trained language model, BERT (and its robustly optimized version RoBERTa), has attracted a lot of attention in natural language understanding (NLU), and achieved state-of-the-art accuracy in various NLU tasks, such as sentiment classification, natural language inference, semantic textual similarity and question answering.
Ranked #1 on
Natural Language Inference
on QNLI
Incorporating Relation Knowledge into Commonsense Reading Comprehension with Multi-task Learning
This paper focuses on how to take advantage of external relational knowledge to improve machine reading comprehension (MRC) with multi-task learning.
Change Detection in Multi-temporal VHR Images Based on Deep Siamese Multi-scale Convolutional Networks
Based on the unit two novel deep siamese convolutional neural networks, called as deep siamese multi-scale convolutional network (DSMS-CN) and deep siamese multi-scale fully convolutional network (DSMS-FCN), are designed for unsupervised and supervised change detection, respectively.
A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer
Unsupervised text style transfer aims to alter text styles while preserving the content, without aligned data for supervision.
ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data
Scene understanding of high resolution aerial images is of great importance for the task of automated monitoring in various remote sensing applications.
A Deep Look into Neural Ranking Models for Information Retrieval
Ranking models lie at the heart of research on information retrieval (IR).
Optimizing seed inputs in fuzzing with machine learning
Our experiments on a set of widely used PDF viewers demonstrate that the improved seed inputs produced by our framework could significantly increase the code coverage of the target program and the likelihood of detecting program crashes.
Cryptography and Security
Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images
In recent years, deep network has shown its brilliant performance in many fields including feature extraction and projection.
Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering
Extensive experiments on the large-scale SQuAD and TriviaQA datasets validate the effectiveness of the proposed method.
A Deep Cascade Model for Multi-Document Reading Comprehension
To address this problem, we develop a novel deep cascade learning model, which progressively evolves from the document-level and paragraph-level ranking of candidate texts to more precise answer extraction with machine reading comprehension.
Ranked #2 on
Question Answering
on MS MARCO
The MWA GLEAM 4-Jy (G4Jy) Sample
These were observed at low radio-frequencies as part of the GaLactic and Extragalactic All-sky MWA (GLEAM) Survey, which is a continuum survey conducted using the Murchison Widefield Array (MWA).
Astrophysics of Galaxies
Object Tracking in Satellite Videos Based on a Multi-Frame Optical Flow Tracker
Object tracking is a hot topic in computer vision.
Multi-class Active Learning: A Hybrid Informative and Representative Criterion Inspired Approach
Simultaneously, our proposed method makes full use of the label information, and the proposed active learning is designed based on multiple classes.
DALiuGE: A Graph Execution Framework for Harnessing the Astronomical Data Deluge
The Data Activated Liu Graph Engine - DALiuGE - is an execution framework for processing large astronomical datasets at a scale required by the Square Kilometre Array Phase 1 (SKA1).
Distributed, Parallel, and Cluster Computing Instrumentation and Detectors
GaLactic and Extragalactic All-sky Murchison Widefield Array (GLEAM) survey I: A low-frequency extragalactic catalogue
Using the Murchison Widefield Array (MWA), the low-frequency Square Kilometre Array (SKA1 LOW) precursor located in Western Australia, we have completed the GaLactic and Extragalactic All-sky MWA (GLEAM) survey, and present the resulting extragalactic catalogue, utilising the first year of observations.
Astrophysics of Galaxies
