Search Results for author:
Found 630 papers, 203 papers with code
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
To improve parallelism and therefore decrease training time, our attention mechanism connects the bottom layer of the decoder to the top layer of the encoder.
Ranked #35 on
Machine Translation
on WMT2014 English-French
Qwen Technical Report
Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans.
Ranked #3 on
Multi-Label Text Classification
on CC3M-TagMask
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections
Large-scale pretrained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks.
Ranked #1 on
Image Captioning
on COCO Captions
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
In contrast to predominant paradigms of solely relying on sequence-to-sequence generation or encoder-based instance discrimination, mPLUG-2 introduces a multi-module composition network by sharing common universal modules for modality collaboration and disentangling different modality modules to deal with modality entanglement.
Ranked #1 on
Video Captioning
on MSR-VTT
Package Recommendation with Intra- and Inter-Package Attention Networks
With the booming of online social networks in the mobile internet, an emerging recommendation scenario has played a vital role in information acquisition for user, where users are no longer recommended with a single item or item list, but a combination of heterogeneous and diverse objects (called a package, e. g., a package including news, publisher, and friends viewing the news).
LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping
We propose a framework for tightly-coupled lidar inertial odometry via smoothing and mapping, LIO-SAM, that achieves highly accurate, real-time mobile robot trajectory estimation and map-building.
Robotics
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.
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
VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation
Existing work in multilingual pretraining has demonstrated the potential of cross-lingual transferability by training a unified Transformer encoder for multiple languages.
StructuralLM: Structural Pre-training for Form Understanding
Large pre-trained language models achieve state-of-the-art results when fine-tuned on downstream NLP tasks.
InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews
This paper, instead, introduces a novel perspective to evaluate the personality fidelity of RPAs with psychological scales.
YUAN 2.0: A Large Language Model with Localized Filtering-based Attention
In this work, we develop and release Yuan 2. 0, a series of large language models with parameters ranging from 2. 1 billion to 102. 6 billion.
A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision.
Interpretable Click-Through Rate Prediction through Hierarchical Attention
For this problem, existing approaches, with shallow or deep architectures, have three major drawbacks.
RRHF: Rank Responses to Align Language Models with Human Feedback without tears
Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models with human preferences, significantly enhancing the quality of interactions between humans and models.
Language-agnostic BERT Sentence Embedding
While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning (Reimers and Gurevych, 2019), BERT based cross-lingual sentence embeddings have yet to be explored.
SimGNN: A Neural Network Approach to Fast Graph Similarity Computation
Our model achieves better generalization on unseen graphs, and in the worst case runs in quadratic time with respect to the number of nodes in two graphs.
Ranked #1 on
Graph Similarity
on IMDb
Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion
In this paper, we formulate PAR as a vision-language fusion problem and fully exploit the relations between pedestrian images and attribute labels.
Approximate Nearest Neighbor Search on High Dimensional Data --- Experiments, Analyses, and Improvement (v1.0)
Approximate Nearest neighbor search (ANNS) is fundamental and essential operation in applications from many domains, such as databases, machine learning, multimedia, and computer vision.
Databases
How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition
We propose four intriguing research questions to explore the association between model performance and various factors including data amount, composition ratio, model size and SFT strategies.
Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
The agent probes the system with, potentially many, natural language reformulations of an initial question and aggregates the returned evidence to yield the best answer.
Convolutional Set Matching for Graph Similarity
We introduce GSimCNN (Graph Similarity Computation via Convolutional Neural Networks) for predicting the similarity score between two graphs.
ChatPLUG: Open-Domain Generative Dialogue System with Internet-Augmented Instruction Tuning for Digital Human
In this paper, we present ChatPLUG, a Chinese open-domain dialogue system for digital human applications that instruction finetunes on a wide range of dialogue tasks in a unified internet-augmented format.
Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks
We propose Additive Powers-of-Two~(APoT) quantization, an efficient non-uniform quantization scheme for the bell-shaped and long-tailed distribution of weights and activations in neural networks.
BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
To further employ the power of quantization, the mixed precision technique is incorporated in our framework by approximating the inter-layer and intra-layer sensitivity.
Unsupervised High-Resolution Portrait Gaze Correction and Animation
Solving this problem using an unsupervised method remains an open problem, especially for high-resolution face images in the wild, which are not easy to annotate with gaze and head pose labels.
Lion: Adversarial Distillation of Proprietary Large Language Models
The practice of transferring knowledge from a sophisticated, proprietary large language model (LLM) to a compact, open-source LLM has garnered considerable attention.
GestureGAN for Hand Gesture-to-Gesture Translation in the Wild
Therefore, this task requires a high-level understanding of the mapping between the input source gesture and the output target gesture.
Ranked #1 on
Gesture-to-Gesture Translation
on NTU Hand Digit
Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts
We verify the effectiveness of the proposed explanations from two aspects: (1) Counterfactual Trace Visualization: the enhanced forgery images are useful to reveal artifacts by visually contrasting the original images and two different visualization methods; (2) Transferable Adversarial Attacks: the adversarial forgery images generated by attacking the detection model are able to mislead other detection models, implying the removed artifacts are general.
Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild
In this paper we address the problem of unsupervised gaze correction in the wild, presenting a solution that works without the need for precise annotations of the gaze angle and the head pose.
HyperLips: Hyper Control Lips with High Resolution Decoder for Talking Face Generation
First, FaceEncoder is used to obtain latent code by extracting features from the visual face information taken from the video source containing the face frame. Then, HyperConv, which weighting parameters are updated by HyperNet with the audio features as input, will modify the latent code to synchronize the lip movement with the audio.
Object-oriented SLAM using Quadrics and Symmetry Properties for Indoor Environments
As objects are often observed locally, the proposed algorithm uses the symmetrical properties of indoor artificial objects to estimate the occluded parts to obtain more accurate quadric parameters.
Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning
To this end, we propose to integrate an Energy-based Hinge loss to enhance the pairwise discriminative power, inspired by the connection between the NT-Xent loss and the Energy-based Learning paradigm.
Ranked #1 on
Semantic Textual Similarity
on CxC
Adapting by Pruning: A Case Study on BERT
Adapting pre-trained neural models to downstream tasks has become the standard practice for obtaining high-quality models.
Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
Recent works have shown the benefit of integrating Conditional Random Fields (CRFs) models into deep architectures for improving pixel-level prediction tasks.
A Survey on Self-Supervised Learning for Non-Sequential Tabular Data
Recently, SSL has been a new trend in exploring the representation learning capability in the realm of tabular data, which is more challenging due to not having explicit relations for learning descriptive representations.
Single-Stage 6D Object Pose Estimation
Second, training the deep network relies on a surrogate loss that does not directly reflect the final 6D pose estimation task.
Graph-based Molecular Representation Learning
Recently, MRL has achieved considerable progress, especially in methods based on deep molecular graph learning.
SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models
Most of the existing Large Language Model (LLM) benchmarks on scientific problem reasoning focus on problems grounded in high-school subjects and are confined to elementary algebraic operations.
Improving MMD-GAN Training with Repulsive Loss Function
To address this issue, we propose a repulsive loss function to actively learn the difference among the real data by simply rearranging the terms in MMD.
Ranked #19 on
Image Generation
on STL-10
Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts
The cross-view association model is learned to bridge the embeddings of ontological concepts and their corresponding instance-view entities.
MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation
To deal with this problem, we propose a novel multi-level statistics transfer model, which disentangles and transfers multi-level appearance features from person images and merges them with pose features to reconstruct the source person images themselves.
Multi-Source Cross-Lingual Model Transfer: Learning What to Share
In this work, we focus on the multilingual transfer setting where training data in multiple source languages is leveraged to further boost target language performance.
Ranked #10 on
Cross-Lingual NER
on CoNLL Dutch
Backpropagation-Friendly Eigendecomposition
Eigendecomposition (ED) is widely used in deep networks.
ShuttleSHAP: A Turn-Based Feature Attribution Approach for Analyzing Forecasting Models in Badminton
Agent forecasting systems have been explored to investigate agent patterns and improve decision-making in various domains, e. g., pedestrian predictions and marketing bidding.
Robust Differentiable SVD
Eigendecomposition of symmetric matrices is at the heart of many computer vision algorithms.
Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation
In this work, we propose a novel Cycle In Cycle Generative Adversarial Network (C$^2$GAN) for the task of keypoint-guided image generation.
UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scene
Finally, we jointly optimize a hyper network to realize the scene photorealistic style transfer of arbitrary style images.
Stereo Plane SLAM Based on Intersecting Lines
Adding such plane features in stereo SLAM system reduces the drift error and refines the performance.
CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents
Within CivRealm, we provide interfaces for two typical agent types: tensor-based agents that focus on learning, and language-based agents that emphasize reasoning.
Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling?
Singular Value Decomposition (SVD) is used in GCP to compute the matrix square root.
Fast Differentiable Matrix Square Root
Previous methods either adopt the Singular Value Decomposition (SVD) to explicitly factorize the matrix or use the Newton-Schulz iteration (NS iteration) to derive the approximate solution.
On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition
Inspired by this observation, we propose a network branch dedicated to magnifying the importance of small eigenvalues.
Ranked #5 on
Fine-Grained Image Classification
on Stanford Dogs
Fine-Grained Image Classification
Fine-Grained Visual Categorization
+1
CFSNet: Toward a Controllable Feature Space for Image Restoration
Deep learning methods have witnessed the great progress in image restoration with specific metrics (e. g., PSNR, SSIM).
DALNet: A Rail Detection Network Based on Dynamic Anchor Line
In the paper, motivated by the anchor line-based lane detection methods, we propose a rail detection network called DALNet based on dynamic anchor line.
MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction
In this work, we propose a novel unsupervised embedding-based KPE approach, Masked Document Embedding Rank (MDERank), to address this problem by leveraging a mask strategy and ranking candidates by the similarity between embeddings of the source document and the masked document.
D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
In this paper, we propose replacing the implicit value with an adaptive uncertainty distribution, to differentiate between points based on their distance to the surface.
Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization
Moreover, we propose a novel Self-Training Part Replacement (STPR) strategy to refine the model for the texture-transfer task, which improves the quality of the generated clothes and the preservation ability of non-target regions.
Content-Variant Reference Image Quality Assessment via Knowledge Distillation
The comparisons of distribution differences between HQ and LQ images can help our model better assess the image quality.
Fast Differentiable Matrix Square Root and Inverse Square Root
Computing the matrix square root and its inverse in a differentiable manner is important in a variety of computer vision tasks.
How well do Large Language Models perform in Arithmetic tasks?
Large language models have emerged abilities including chain-of-thought to answer math word problems step by step.
Empirical Bayes Matrix Factorization
This yields a sparse EBMF approach - essentially a version of sparse FA/PCA - that automatically adapts the amount of sparsity to the data.
Methodology
Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
We introduce a novel approach to graph-level representation learning, which is to embed an entire graph into a vector space where the embeddings of two graphs preserve their graph-graph proximity.
Ranked #1 on
Graph Classification
on Web
Intelligent Reflecting Surface Configurations for Smart Radio Using Deep Reinforcement Learning
Intelligent reflecting surface (IRS) is envisioned to change the paradigm of wireless communications from "adapting to wireless channels" to "changing wireless channels".
Deep Discriminative Feature Learning for Accent Recognition
Accent recognition with deep learning framework is a similar work to deep speaker identification, they're both expected to give the input speech an identifiable representation.
Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generation
Generative Neural Radiance Fields (GNeRF) based 3D-aware GANs have demonstrated remarkable capabilities in generating high-quality images while maintaining strong 3D consistency.
Learning-based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching
Since computing the exact distance/similarity between two graphs is typically NP-hard, a series of approximate methods have been proposed with a trade-off between accuracy and speed.
Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
State-of-the-art methods for image-to-image translation with Generative Adversarial Networks (GANs) can learn a mapping from one domain to another domain using unpaired image data.
Generative Adversarial Network
Image-to-Image Translation
+1
SO-SLAM: Semantic Object SLAM with Scale Proportional and Symmetrical Texture Constraints
Object SLAM introduces the concept of objects into Simultaneous Localization and Mapping (SLAM) and helps understand indoor scenes for mobile robots and object-level interactive applications.
Diffusion for Natural Image Matting
However, the presence of high computational overhead and the inconsistency of noise sampling between the training and inference processes pose significant obstacles to achieving this goal.
Ranked #1 on
Image Matting
on Distinctions-646
Learning Gender-Neutral Word Embeddings
Word embedding models have become a fundamental component in a wide range of Natural Language Processing (NLP) applications.
Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference
There has been a steady need in the medical community to precisely extract the temporal relations between clinical events.
Mixup for Node and Graph Classification
In this work, we propose the Mixup methods for two fundamental tasks in graph learning: node and graph classification.
Ranked #16 on
Node Classification
on Pubmed
Optimal Transport for Unsupervised Denoising Learning
Toward answering this question, this work proposes a criterion for unsupervised denoising learning based on the optimal transport theory.
FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models
To fill this research gap, in this paper, we propose FollowBench, a Multi-level Fine-grained Constraints Following Benchmark for LLMs.
Deep Micro-Dictionary Learning and Coding Network
In this paper, we propose a novel Deep Micro-Dictionary Learning and Coding Network (DDLCN).
A Quantitative Survey of Communication Optimizations in Distributed Deep Learning
In this article, we present a quantitative survey of communication optimization techniques for data parallel distributed DL.
RiDDLE: Reversible and Diversified De-identification with Latent Encryptor
This work presents RiDDLE, short for Reversible and Diversified De-identification with Latent Encryptor, to protect the identity information of people from being misused.
HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion
LiDAR relocalization plays a crucial role in many fields, including robotics, autonomous driving, and computer vision.
Rafiki: Machine Learning as an Analytics Service System
Second, expertise knowledge is required to optimize the training and inference procedures in terms of efficiency and effectiveness, which imposes heavy burden on the system users.
Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers
In particular, MJP first shuffles the selected patches via our block-wise random jigsaw puzzle shuffle algorithm, and their corresponding PEs are occluded.
3D-Aware Semantic-Guided Generative Model for Human Synthesis
However, they usually struggle to generate high-quality images representing non-rigid objects, such as the human body, which is of a great interest for many computer graphics applications.
Learning A Coarse-to-Fine Diffusion Transformer for Image Restoration
Specifically, our C2F-DFT contains diffusion self-attention (DFSA) and diffusion feed-forward network (DFN) within a new coarse-to-fine training scheme.
Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks
Molecular Representation Learning (MRL) has proven impactful in numerous biochemical applications such as drug discovery and enzyme design.
Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
In this paper, we propose to learn system dynamics from irregularly-sampled partial observations with underlying graph structure for the first time.
Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment
In this paper, we explore multilingual KG completion, which leverages limited seed alignment as a bridge, to embrace the collective knowledge from multiple languages.
Ranked #3 on
Knowledge Graph Completion
on DPB-5L (French)
DFGC 2021: A DeepFake Game Competition
This competition provides a common platform for benchmarking the adversarial game between current state-of-the-art DeepFake creation and detection methods.
Wasserstein Adversarial Transformer for Cloud Workload Prediction
Understanding the job arrival rate is crucial for accurately predicting future changes in cloud workloads and proactively provisioning and de-provisioning VMs for hosting the applications.
NLUT: Neural-based 3D Lookup Tables for Video Photorealistic Style Transfer
However, existing methods obtain stylized video sequences by performing frame-by-frame photorealistic style transfer, which is inefficient and does not ensure the temporal consistency of the stylized video.
Transferable Sparse Adversarial Attack
The experiment shows that our method has improved the transferability by a large margin under a similar sparsity setting compared with state-of-the-art methods.
Towards Fine-Grained Reasoning for Fake News Detection
The detection of fake news often requires sophisticated reasoning skills, such as logically combining information by considering word-level subtle clues.
Improving Event Representation via Simultaneous Weakly Supervised Contrastive Learning and Clustering
Representations of events described in text are important for various tasks.
Understanding Architectures Learnt by Cell-based Neural Architecture Search
Neural architecture search (NAS) searches architectures automatically for given tasks, e. g., image classification and language modeling.
Transformer Network for Significant Stenosis Detection in CCTA of Coronary Arteries
However, the complexity of coronary artery plaques that cause CAD makes the automatic detection of coronary artery stenosis in Coronary CT angiography (CCTA) a difficult task.
Coupled Graph ODE for Learning Interacting System Dynamics
On one hand, features of objects change over time, influenced by the linked objects in the interaction graph.
QAQ: Quality Adaptive Quantization for LLM KV Cache
The emergence of LLMs has ignited a fresh surge of breakthroughs in NLP applications, particularly in domains such as question-answering systems and text generation.
Dynamic Malware Analysis with Feature Engineering and Feature Learning
In this paper, we propose a novel and low-cost feature extraction approach, and an effective deep neural network architecture for accurate and fast malware detection.
COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas
In this work, we propose COSPLAY(COncept Set guided PersonaLized dialogue generation Across both partY personas) that considers both parties as a "team": expressing self-persona while keeping curiosity toward the partner, leading responses around mutual personas, and finding the common ground.
Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation
Thus, recent studies concern about adversarial distillation (AD) that aims to inherit not only prediction accuracy but also adversarial robustness of a robust teacher model under the paradigm of robust optimization.
TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation
The research focus of scene text detection and recognition has shifted to arbitrary shape text in recent years, where the text shape representation is a fundamental problem.
Ranked #5 on
Text Spotting
on SCUT-CTW1500
CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inference
To this end, we develop an approach that can effectively take advantage of the sparsity of matrix operations in GCN inference to significantly reduce the computational overhead.
Source-LDA: Enhancing probabilistic topic models using prior knowledge sources
The approach taken is to complement the existing topic distributions over words with a known distribution based on a predefined set of topics.
TSDM: Tracking by SiamRPN++ with a Depth-refiner and a Mask-generator
The D-r optimizes the target bounding box estimated by SiamRPN++, based on the spatial depth distribution difference between the target and the surrounding background.
StyleDGPT: Stylized Response Generation with Pre-trained Language Models
Generating responses following a desired style has great potentials to extend applications of open-domain dialogue systems, yet is refrained by lacking of parallel data for training.
Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets
Time series modeling has attracted extensive research efforts; however, achieving both reliable efficiency and interpretability from a unified model still remains a challenging problem.
Conditional Hyper-Network for Blind Super-Resolution with Multiple Degradations
We extract degradation prior at task-level with the proposed ConditionNet, which will be used to adapt the parameters of the basic SR network (BaseNet).
Proximal Policy Optimization with Mixed Distributed Training
Instability and slowness are two main problems in deep reinforcement learning.
RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection
The task of out-of-distribution (OOD) detection is crucial for deploying machine learning models in real-world settings.
RankFeat&RankWeight: Rank-1 Feature/Weight Removal for Out-of-distribution Detection
This observation motivates us to propose \texttt{RankFeat}, a simple yet effective \emph{post hoc} approach for OOD detection by removing the rank-1 matrix composed of the largest singular value and the associated singular vectors from the high-level feature.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Fixed-Parameter Tractable Sampling for RNA Design with Multiple Target Structures
The design of multi-stable RNA molecules has important applications in biology, medicine, and biotechnology.
Quantitative Methods
Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation
However, in machine learning, this cross-modal learning is a nontrivial task because different modalities have no homogeneous properties.
Motion Prediction Using Temporal Inception Module
We argue that the diverse temporal scales are important as they allow us to look at the past frames with different receptive fields, which can lead to better predictions.
Learning Deep Network Representations with Adversarially Regularized Autoencoders
The problem of network representation learning, also known as network embedding, arises in many machine learning tasks assuming that there exist a small number of variabilities in the vertex representations which can capture the "semantics" of the original network structure.
Batch-efficient EigenDecomposition for Small and Medium Matrices
EigenDecomposition (ED) is at the heart of many computer vision algorithms and applications.
Drug-Target Interaction Prediction with Graph Attention networks
For better learning and interpreting the DTI topological structure and the similarity, it is desirable to have methods specifically for predicting interactions from the graph structure.
FLASHE: Additively Symmetric Homomorphic Encryption for Cross-Silo Federated Learning
Homomorphic encryption (HE) is a promising privacy-preserving technique for cross-silo federated learning (FL), where organizations perform collaborative model training on decentralized data.
PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition
In this paper, we propose a Parallel, Iterative and Mimicking Network (PIMNet) to balance accuracy and efficiency.
Derivative Delay Embedding: Online Modeling of Streaming Time Series
The staggering amount of streaming time series coming from the real world calls for more efficient and effective online modeling solution.
Lightweight Feature Fusion Network for Single Image Super-Resolution
Specifically, a spindle block is composed of a dimension extension unit, a feature exploration unit and a feature refinement unit.
Ranked #11 on
Image Super-Resolution
on Manga109 - 3x upscaling
Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification
To identify adversarial attacks, a perturbation discriminator validates how likely a token in the text is perturbed and provides a set of potential perturbations.
Long Document Ranking with Query-Directed Sparse Transformer
In this paper, we design Query-Directed Sparse attention that induces IR-axiomatic structures in transformer self-attention.
Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives
Following SimCSE, contrastive learning based methods have achieved the state-of-the-art (SOTA) performance in learning sentence embeddings.
Householder Projector for Unsupervised Latent Semantics Discovery
Generative Adversarial Networks (GANs), especially the recent style-based generators (StyleGANs), have versatile semantics in the structured latent space.
Learning to Edit: Aligning LLMs with Knowledge Editing
Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention.
Predicting Aqueous Solubility of Organic Molecules Using Deep Learning Models with Varied Molecular Representations
Determining the aqueous solubility of molecules is a vital step in many pharmaceutical, environmental, and energy storage applications.
Ranking Causal Anomalies via Temporal and Dynamical Analysis on Vanishing Correlations
Structures and evolutions of the invariance network, in particular the vanishing correlations, can shed important light on locating causal anomalies and performing diagnosis.
Code Recommendation for Open Source Software Developers
In this paper, we formulate the novel problem of code recommendation, whose purpose is to predict the future contribution behaviors of developers given their interaction history, the semantic features of source code, and the hierarchical file structures of projects.
A deep network for sinogram and CT image reconstruction
A CT image can be well reconstructed when the sampling rate of the sinogram satisfies the Nyquist criteria and the sampled signal is noise-free.
AnomalyHop: An SSL-based Image Anomaly Localization Method
An image anomaly localization method based on the successive subspace learning (SSL) framework, called AnomalyHop, is proposed in this work.
Synthetic Data Supervised Salient Object Detection
In this paper, we propose a novel yet effective method for SOD, coined SODGAN, which can generate infinite high-quality image-mask pairs requiring only a few labeled data, and these synthesized pairs can replace the human-labeled DUTS-TR to train any off-the-shelf SOD model.
A Generative Approach for Script Event Prediction via Contrastive Fine-tuning
First, the pretrained language models adopted by current works ignore event-level knowledge, resulting in an inability to capture the correlations between events well.
A Deep Learning-based Quality Assessment and Segmentation System with a Large-scale Benchmark Dataset for Optical Coherence Tomographic Angiography Image
The large-scale OCTA dataset is available at https://doi. org/10. 5281/zenodo. 5111975, https://doi. org/10. 5281/zenodo. 5111972.
Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality
Inserting an SVD meta-layer into neural networks is prone to make the covariance ill-conditioned, which could harm the model in the training stability and generalization abilities.
Orthogonal SVD Covariance Conditioning and Latent Disentanglement
Extensive experiments on visual recognition demonstrate that our methods can simultaneously improve covariance conditioning and generalization.
ECGadv: Generating Adversarial Electrocardiogram to Misguide Arrhythmia Classification System
Deep neural networks (DNNs)-powered Electrocardiogram (ECG) diagnosis systems recently achieve promising progress to take over tedious examinations by cardiologists.
Attribute-Guided Sketch Generation
To this end, we propose a novel Attribute-Guided Sketch Generative Adversarial Network (ASGAN) which is an end-to-end framework and contains two pairs of generators and discriminators, one of which is used to generate faces with attributes while the other one is employed for image-to-sketch translation.
DFGC 2022: The Second DeepFake Game Competition
There is a two-party game between DeepFake creators and defenders.
Global and Local Hierarchy-aware Contrastive Framework for Implicit Discourse Relation Recognition
Due to the absence of explicit connectives, implicit discourse relation recognition (IDRR) remains a challenging task in discourse analysis.
SenWave: Monitoring the Global Sentiments under the COVID-19 Pandemic
Since the first alert launched by the World Health Organization (5 January, 2020), COVID-19 has been spreading out to over 180 countries and territories.
Incorporating External POS Tagger for Punctuation Restoration
Punctuation restoration is an important post-processing step in automatic speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Position-prior Clustering-based Self-attention Module for Knee Cartilage Segmentation
The morphological changes in knee cartilage (especially femoral and tibial cartilages) are closely related to the progression of knee osteoarthritis, which is expressed by magnetic resonance (MR) images and assessed on the cartilage segmentation results.
DeAR: Accelerating Distributed Deep Learning with Fine-Grained All-Reduce Pipelining
Communication scheduling has been shown to be effective in accelerating distributed training, which enables all-reduce communications to be overlapped with backpropagation computations.
DeepFirearm: Learning Discriminative Feature Representation for Fine-grained Firearm Retrieval
There are great demands for automatically regulating inappropriate appearance of shocking firearm images in social media or identifying firearm types in forensics.
A flexible empirical Bayes approach to multiple linear regression and connections with penalized regression
We introduce a new empirical Bayes approach for large-scale multiple linear regression.
An Automatic Cardiac Segmentation Framework based on Multi-sequence MR Image
A CNN segmentation model was trained based on the augmented training data by leave-one-out strategy.
Learning Pose-invariant 3D Object Reconstruction from Single-view Images
Learning to reconstruct 3D shapes using 2D images is an active research topic, with benefits of not requiring expensive 3D data.
PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization
In this paper, we present a novel end-to-end learning-based LiDAR relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input, without requiring a pre-built map.
Robotics
ULTRA: Uncertainty-aware Label Distribution Learning for Breast Tumor Cellularity Assessment
Therefore, automatic TC estimation is significant in clinical practice.
Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environment
In this paper, we formulate such problems as Evolving Domain Generalization, where a model aims to generalize well on a target domain by discovering and leveraging the evolving pattern of the environment.
TLNets: Transformation Learning Networks for long-range time-series prediction
Note that the FT and SVD blocks are capable of learning global information, while the Conv blocks focus on learning local information.
Know2BIO: A Comprehensive Dual-View Benchmark for Evolving Biomedical Knowledge Graphs
Knowledge graphs (KGs) have emerged as a powerful framework for representing and integrating complex biomedical information.
Recommending Themes for Ad Creative Design via Visual-Linguistic Representations
There is a perennial need in the online advertising industry to refresh ad creatives, i. e., images and text used for enticing online users towards a brand.
Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations
Different from previous cross-domain FSL work (CD-FSL) that considers the domain shift between base and novel classes, the new problem, termed cross-domain cross-set FSL (CDSC-FSL), requires few-shot learners not only to adapt to the new domain, but also to be consistent between different domains within each novel class.
Deep Learning for Single Image Super-Resolution: A Brief Review
Single image super-resolution (SISR) is a notoriously challenging ill-posed problem, which aims to obtain a high-resolution (HR) output from one of its low-resolution (LR) versions.
LCSCNet: Linear Compressing Based Skip-Connecting Network for Image Super-Resolution
In this paper, we develop a concise but efficient network architecture called linear compressing based skip-connecting network (LCSCNet) for image super-resolution.
Ranked #14 on
Image Super-Resolution
on Set14 - 3x upscaling
Revisit Systematic Generalization via Meaningful Learning
Humans can systematically generalize to novel compositions of existing concepts.
Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition
However, for the current state-of-the-art(SOTA) methods, there is room for improvement in terms of the efficient usage of local visual and global context information of the input text image, as well as the robust correlation between the scene processing module(encoder) and the text processing module(decoder).
Ranked #14 on
Scene Text Recognition
on ICDAR2015
How to best use Syntax in Semantic Role Labelling
There are many different ways in which external information might be used in an NLP task.
Degree-Aware Alignment for Entities in Tail
Entity alignment (EA) is to discover equivalent entities in knowledge graphs (KGs), which bridges heterogeneous sources of information and facilitates the integration of knowledge.
A Dataset and Baselines for Multilingual Reply Suggestion
Reply suggestion models help users process emails and chats faster.
PI-Trans: Parallel-ConvMLP and Implicit-Transformation Based GAN for Cross-View Image Translation
For semantic-guided cross-view image translation, it is crucial to learn where to sample pixels from the source view image and where to reallocate them guided by the target view semantic map, especially when there is little overlap or drastic view difference between the source and target images.
Linear-scaling kernels for protein sequences and small molecules outperform deep learning while providing uncertainty quantitation and improved interpretability
We compare the performance of xGPR with the reported performance of various deep learning models on 20 benchmarks, including small molecule, protein sequence and tabular data.
Ranked #8 on
Formation Energy
on QM9
Bi-Level Attention Graph Neural Networks
Recent graph neural networks (GNNs) with the attention mechanism have historically been limited to small-scale homogeneous graphs (HoGs).
Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation
In this paper, we study the application of Test-time domain adaptation in semantic segmentation (TTDA-Seg) where both efficiency and effectiveness are crucial.
Learning by Analogy: Diverse Questions Generation in Math Word Problem
We then feed them to a question generator together with the scenario to obtain the corresponding diverse questions, forming a new MWP with a variety of questions and equations.
PGraphDTA: Improving Drug Target Interaction Prediction using Protein Language Models and Contact Maps
Through extensive experimentation, we demonstrate that our proposed approaches outperform the baseline models considered in this study, presenting a compelling case for further development in this direction.
Ranked #1 on
on DAVIS-DTA
Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
We even conceived a neuro-symbolic reasoning approach that reconciles LLMs & VLMs with logical reasoning to emulate the human problem-solving process for Bongard Problems.
Ranked #1 on
Visual Reasoning
on Bongard-OpenWorld
Hierarchical Attention Models for Multi-Relational Graphs
BR-GCN models use bi-level attention to learn node embeddings through (1) node-level attention, and (2) relation-level attention.
"The Boating Store Had Its Best Sail Ever": Pronunciation-attentive Contextualized Pun Recognition
In this paper, we propose Pronunciation-attentive Contextualized Pun Recognition (PCPR) to perceive human humor, detect if a sentence contains puns and locate them in the sentence.
Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer
We study Comparative Preference Classification (CPC) which aims at predicting whether a preference comparison exists between two entities in a given sentence and, if so, which entity is preferred over the other.
Counterfactual Adversarial Learning with Representation Interpolation
Deep learning models exhibit a preference for statistical fitting over logical reasoning.
A Recurrent Model for Collective Entity Linking with Adaptive Features
Traditional machine learning based methods for NED were outperformed and made obsolete by the state-of-the-art deep learning based models.
Gotta: Generative Few-shot Question Answering by Prompt-based Cloze Data Augmentation
Few-shot question answering (QA) aims at precisely discovering answers to a set of questions from context passages while only a few training samples are available.
Contextual Regression: An Accurate and Conveniently Interpretable Nonlinear Model for Mining Discovery from Scientific Data
We demonstrate its high prediction accuracy and sensitivity through the task of predictive feature selection on a simulated dataset and the application of predicting open chromatin sites in the human genome.
Consistent and Flexible Selectivity Estimation for High-Dimensional Data
Selectivity estimation aims at estimating the number of database objects that satisfy a selection criterion.
Scalable K-FAC Training for Deep Neural Networks with Distributed Preconditioning
The second-order optimization methods, notably the D-KFAC (Distributed Kronecker Factored Approximate Curvature) algorithms, have gained traction on accelerating deep neural network (DNN) training on GPU clusters.
BotHawk: An Approach for Bots Detection in Open Source Software Projects
Identifying bot accounts and behavior is a challenging task in the OSS project.
Unsupervised Decomposition Networks for Bias Field Correction in MR Image
Many retrospective algorithms were developed to facilitate the bias correction, to which the deep learning-based methods outperformed.
Bidirectional Alignment for Domain Adaptive Detection with Transformers
We propose a Bidirectional Alignment for domain adaptive Detection with Transformers (BiADT) to improve cross domain object detection performance.
Dataset Distillation via Adversarial Prediction Matching
This ensures the memory efficiency of our method and provides a flexible tradeoff between time and memory budgets, allowing us to distil ImageNet-1K using a minimum of only 6. 5GB of GPU memory.
Kinship Identification through Joint Learning Using Kinship Verification Ensembles
The experiments further show significant performance improvement of kinship verification when trained on the same dataset with more realistic distributions.
Unsupervised Natural Language Inference via Decoupled Multimodal Contrastive Learning
MACD forces the decoupled text encoder to represent the visual information via contrastive learning.
Bio-JOIE: Joint Representation Learning of Biological Knowledge Bases
Leveraging a wide-range of biological knowledge, such as gene ontology and protein-protein interaction (PPI) networks from other closely related species presents a vital approach to infer the molecular impact of a new species.
Dual-Geometric Space Embedding Model for Two-View Knowledge Graphs
For works that seek to put both views of the KG together, the instance and ontology views are assumed to belong to the same geometric space, such as all nodes embedded in the same Euclidean space or non-Euclidean product space, an assumption no longer reasonable for two-view KGs where different portions of the graph exhibit different structures.
What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?
Based on the evaluation results, we also identify the best choices for different factors and propose a new multi-scale image feature representation method to encode the image effectively.
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).
Self Organizing Nebulous Growths for Robust and Incremental Data Visualization
In addition, SONG is capable of handling new data increments, no matter whether they are similar or heterogeneous to the already observed data distribution.
Progressive Cluster Purification for Unsupervised Feature Learning
In this work, we propose a novel clustering based method, which, by iteratively excluding class inconsistent samples during progressive cluster formation, alleviates the impact of noise samples in a simple-yet-effective manner.
A model-guided deep network for limited-angle computed tomography
In this paper, we first propose a variational model for the limited-angle computed tomography (CT) image reconstruction and then convert the model into an end-to-end deep network. We use the penalty method to solve the model and divide it into three iterative subproblems, where the first subproblem completes the sinograms by utilizing the prior information of sinograms in the frequency domain and the second refines the CT images by using the prior information of CT images in the spatial domain, and the last merges the outputs of the first two subproblems.
Neural network facilitated ab initio derivation of linear formula: A case study on formulating the relationship between DNA motifs and gene expression
We showed that this linear model could predict gene expression levels using promoter sequences with a performance comparable to deep neural network models.
Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making
Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks.
Memory-Efficient and Secure DNN Inference on TrustZone-enabled Consumer IoT Devices
We design a memory-efficient management method to support memory-demanding inference in TEEs.
Object Detectors in the Open Environment: Challenges, Solutions, and Outlook
This paper aims to bridge this gap by conducting a comprehensive review and analysis of object detectors in open environments.
TablePuppet: A Generic Framework for Relational Federated Learning
In this paper, we formalize this problem as relational federated learning (RFL).
Semi-Dynamic Load Balancing: Efficient Distributed Learning in Non-Dedicated Environments
Efficient model training requires eliminating such stragglers, yet for modern ML workloads, existing load balancing strategies are inefficient and even infeasible.
Object-Level Representation Learning for Few-Shot Image Classification
Few-shot learning that trains image classifiers over few labeled examples per category is a challenging task.
Pose-Based Two-Stream Relational Networks for Action Recognition in Videos
Second, few pose-based methods model the action-related objects in recognizing human-object interaction actions in which objects play an important role.
Action Recognition In Videos
Human-Object Interaction Detection
+2
Network Reconstruction and Controlling Based on Structural Regularity Analysis
In addition, the model is capable of measuring the importance of microscopic network elements, i. e., nodes and links, in terms of network regularity thereby allowing us to regulate the reconstructability of networks based on them.
Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning
Skeleton-based action recognition has made great progress recently, but many problems still remain unsolved.
Ranked #81 on
Skeleton Based Action Recognition
on NTU RGB+D
PANDA: Facilitating Usable AI Development
In many complex applications such as healthcare, subject matter experts (e. g. Clinicians) are the ones who appreciate the importance of features that affect health, and their knowledge together with existing knowledge bases are critical to the end results.
