Search Results for author:
Found 277 papers, 140 papers with code
It is AI’s Turn to Ask Humans a Question: Question-Answer Pair Generation for Children’s Story Books
Existing question answering (QA) techniques are created mainly to answer questions asked by humans.
SSEGCN: Syntactic and Semantic Enhanced Graph Convolutional Network for Aspect-based Sentiment Analysis
Furthermore, to combine syntactic structure and semantic information, we equip the attention score matrices by syntactic mask matrices.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension
Through benchmarking with QG models, we show that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions.
TL-Explorer: A Digital Humanities Tool for Mapping and Analyzing Translated Literature
TL-Explorer is a digital humanities tool for mapping and analyzing translated literature, encompassing the World Map and the Translation Dashboard.
Region Graph Embedding Network for Zero-Shot Learning
To exploit the progressive interactions among these regions, we represent them as a region graph, on which the parts relation reasoning is performed with graph convolutions, thus leading to our PRR branch.
MovieChats: Chat like Humans in a Closed Domain
In this work, we take a close look at the movie domain and present a large-scale high-quality corpus with fine-grained annotations in hope of pushing the limit of movie-domain chatbots.
{\mathcal{P}^2}: A Plan-and-Pretrain Approach for Knowledge Graph-to-Text Generation
Text verbalization of knowledge graphs is an important problem with wide application to natural language generation (NLG) systems.
DreamPBR: Text-driven Generation of High-resolution SVBRDF with Multi-modal Guidance
Prior material creation methods had limitations in producing diverse results mainly because reconstruction-based methods relied on real-world measurements and generation-based methods were trained on relatively small material datasets.
MHLR: Moving Haar Learning Rate Scheduler for Large-scale Face Recognition Training with One GPU
MHLR supports large-scale FR training with only one GPU, which is able to accelerate the model to 1/4 of its original training time without sacrificing more than 1% accuracy.
Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective
Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences.
Position-Aware Parameter Efficient Fine-Tuning Approach for Reducing Positional Bias in LLMs
Recent advances in large language models (LLMs) have enhanced their ability to process long input contexts.
PID Control-Based Self-Healing to Improve the Robustness of Large Language Models
This approach reduces the computational cost to that of using just the P controller, instead of the full PID control.
EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphs
In this work, we propose an initial comprehensive framework called EventGround, which aims to tackle the problem of grounding free-texts to eventuality-centric KGs for contextualized narrative reasoning.
CDIMC-net: Cognitive Deep Incomplete Multi-view Clustering Network
In this paper, we propose a novel incomplete multi-view clustering network, called Cognitive Deep Incomplete Multi-view Clustering Network (CDIMC-net), to address these issues.
Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splatting
3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis results while advancing real-time rendering performance.
PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model
PSALM is a powerful extension of the Large Multi-modal Model (LMM) to address the segmentation task challenges.
Generalized Referring Expression Segmentation
Image Segmentation
+5
Common 7B Language Models Already Possess Strong Math Capabilities
This paper shows that the LLaMA-2 7B model with common pre-training already exhibits strong mathematical abilities, as evidenced by its impressive accuracy of 97. 7% and 72. 0% on the GSM8K and MATH benchmarks, respectively, when selecting the best response from 256 random generations.
OffLanDat: A Community Based Implicit Offensive Language Dataset Generated by Large Language Model Through Prompt Engineering
Firstly, the existing datasets primarily rely on the collection of texts containing explicit offensive keywords, making it challenging to capture implicitly offensive contents that are devoid of these keywords.
Distilling Large Language Models for Text-Attributed Graph Learning
To address the inherent gaps between LLMs (generative models for texts) and graph models (discriminative models for graphs), we propose first to let LLMs teach an interpreter with rich textual rationale and then let a student model mimic the interpreter's reasoning without LLMs' textual rationale.
LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models
Various parameter-efficient fine-tuning (PEFT) techniques have been proposed to enable computationally efficient fine-tuning while maintaining model performance.
Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance
Multi-agent generative adversarial imitation learning (MAGAIL) allows multi-AUV to learn from expert demonstration instead of pre-defined reward functions, but suffers from the deficiency of requiring optimal demonstrations and not surpassing provided expert demonstrations.
See the Unseen: Better Context-Consistent Knowledge-Editing by Noises
In this paper, we empirically find that the effects of different contexts upon LLMs in recalling the same knowledge follow a Gaussian-like distribution.
Real-Time FJ/MAC PDE Solvers via Tensorized, Back-Propagation-Free Optical PINN Training
Despite the ultra-high speed of optical neural networks, training a PINN on an optical chip is hard due to (1) the large size of photonic devices, and (2) the lack of scalable optical memory devices to store the intermediate results of back-propagation (BP).
Zero-1-to-3: Domain-level Zero-shot Cognitive Diagnosis via One Batch of Early-bird Students towards Three Diagnostic Objectives
Consequently, we refine the cognitive states of cold-start students as diagnostic outcomes via virtual data, aligning with the diagnosis-oriented goal.
Generate E-commerce Product Background by Integrating Category Commonality and Personalized Style
Furthermore, for products with specific and fine-grained requirements in layout, elements, etc, a Personality-Wise Generator is devised to learn such personalized style directly from a reference image to resolve textual ambiguities, and is trained in a self-supervised manner for more efficient training data usage.
Non-Euclidean Spatial Graph Neural Network
Besides, existing spatial network representation learning methods can only consider networks embedded in Euclidean space, and can not well exploit the rich geometric information carried by irregular and non-uniform non-Euclidean space.
Planning and Rendering: Towards End-to-End Product Poster Generation
At the planning stage, we propose a PlanNet to generate the layout of the product and other visual components considering both the appearance features of the product and semantic features of the text, which improves the diversity and rationality of the layouts.
BiPFT: Binary Pre-trained Foundation Transformer with Low-rank Estimation of Binarization Residual Polynomials
Specifically, we first analyze the binarization error in self-attention operations and derive the polynomials of binarization error.
Segment and Caption Anything
We propose a method to efficiently equip the Segment Anything Model (SAM) with the ability to generate regional captions.
RTQ: Rethinking Video-language Understanding Based on Image-text Model
Recent advancements in video-language understanding have been established on the foundation of image-text models, resulting in promising outcomes due to the shared knowledge between images and videos.
Ranked #9 on
Video Retrieval
on MSR-VTT-1kA
Learning to Complement with Multiple Humans (LECOMH): Integrating Multi-rater and Noisy-Label Learning into Human-AI Collaboration
The advent of learning with noisy labels (LNL), multi-rater learning, and human-AI collaboration has revolutionised the development of robust classifiers, enabling them to address the challenges posed by different types of data imperfections and complex decision processes commonly encountered in real-world applications.
Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus
Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields.
A Self-enhancement Approach for Domain-specific Chatbot Training via Knowledge Mining and Digest
This paper introduces a novel approach to enhance LLMs by effectively extracting the relevant knowledge from domain-specific textual sources, and the adaptive training of a chatbot with domain-specific inquiries.
Asymptotically Fair Participation in Machine Learning Models: an Optimal Control Perspective
Moreover, we design a surrogate retention system based on existing literature on evolutionary population dynamics to approximate the dynamics of distribution shifts on active user counts, from which the objective of achieving asymptotically fair participation is formulated as an optimal control problem, and the control variables are considered as the model parameters.
WinNet:time series forecasting with a window-enhanced period extracting and interacting
We present a highly accurate and simply structured CNN-based model for long-term time series forecasting tasks, called WinNet, including (i) Inter-Intra Period Encoder (I2PE) to transform 1D sequence into 2D tensor with long and short periodicity according to the predefined periodic window, (ii) Two-Dimensional Period Decomposition (TDPD) to model period-trend and oscillation terms, and (iii) Decomposition Correlation Block (DCB) to leverage the correlations of the period-trend and oscillation terms to support the prediction tasks by CNNs.
FP8-LM: Training FP8 Large Language Models
In this paper, we explore FP8 low-bit data formats for efficient training of large language models (LLMs).
Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-Thoughts
As large language models (LLMs) have shown effectiveness with different prompting methods, such as Chain of Thought, Program of Thought, we find that these methods have formed a great complementarity to each other on math reasoning tasks.
Semantic-Aware Adversarial Training for Reliable Deep Hashing Retrieval
Further, we, for the first time, formulate the formalized adversarial training of deep hashing into a unified minimax optimization under the guidance of the generated mainstay codes.
StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding
Analogy-making between narratives is crucial for human reasoning.
Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity
This survey addresses the crucial issue of factuality in Large Language Models (LLMs).
Balancing Specialized and General Skills in LLMs: The Impact of Modern Tuning and Data Strategy
This paper introduces a multifaceted methodology for fine-tuning and evaluating large language models (LLMs) for specialized monetization tasks.
Large Language Models for Spatial Trajectory Patterns Mining
Identifying anomalous human spatial trajectory patterns can indicate dynamic changes in mobility behavior with applications in domains like infectious disease monitoring and elderly care.
Beyond Text: A Deep Dive into Large Language Models' Ability on Understanding Graph Data
Large language models (LLMs) have achieved impressive performance on many natural language processing tasks.
Transferable Deep Clustering Model
Deep learning has shown remarkable success in the field of clustering recently.
DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training
Our extensive experiments show that DeepZero achieves state-of-the-art (SOTA) accuracy on ResNet-20 trained on CIFAR-10, approaching FO training performance for the first time.
KLoB: a Benchmark for Assessing Knowledge Locating Methods in Language Models
KLoB can serve as a benchmark for evaluating existing locating methods in language models, and can contributes a method to reassessing the validity of locality hypothesis of factual knowledge.
Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation
Furthermore, we propose a multi-view fusion layer based temporal module which is equipped with a set of object slots and interacts with features from different views by attention mechanism to fulfill sufficient object representation completion.
Partition-A-Medical-Image: Extracting Multiple Representative Sub-regions for Few-shot Medical Image Segmentation
In this work, we present an approach to extract multiple representative sub-regions from a given support medical image, enabling fine-grained selection over the generated image regions.
Unsupervised Open-Vocabulary Object Localization in Videos
In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video object localization.
FLM-101B: An Open LLM and How to Train It with $100K Budget
We demonstrate that a 101B-parameter LLM with 0. 31T tokens can be trained with a budget of 100K US dollars.
InstructDiffusion: A Generalist Modeling Interface for Vision Tasks
We present InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.
Object-Centric Multiple Object Tracking
Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines.
Coarse-to-Fine Amodal Segmentation with Shape Prior
To address this issue, we propose a convolution refine module to inject fine-grained information and provide a more precise amodal object segmentation based on visual features and coarse-predicted segmentation.
Cross-Modal Retrieval: A Systematic Review of Methods and Future Directions
With the exponential surge in diverse multi-modal data, traditional uni-modal retrieval methods struggle to meet the needs of users demanding access to data from various modalities.
Tensor-Compressed Back-Propagation-Free Training for (Physics-Informed) Neural Networks
Backward propagation (BP) is widely used to compute the gradients in neural network training.
DETR Doesn't Need Multi-Scale or Locality Design
This paper presents an improved DETR detector that maintains a "plain" nature: using a single-scale feature map and global cross-attention calculations without specific locality constraints, in contrast to previous leading DETR-based detectors that reintroduce architectural inductive biases of multi-scale and locality into the decoder.
KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection
Achieving a reliable LiDAR-based object detector in autonomous driving is paramount, but its success hinges on obtaining large amounts of precise 3D annotations.
Partial Vessels Annotation-based Coronary Artery Segmentation with Self-training and Prototype Learning
To this end, we propose partial vessels annotation (PVA) based on the challenges of coronary artery segmentation and clinical diagnostic characteristics.
A review of dynamics design methods for high-speed and high-precision CNC machine tool feed systems
With the development of CNC machine tools toward high speed and high precision, the traditional static design methods can hardly meet the demand.
Mutual Query Network for Multi-Modal Product Image Segmentation
Product image segmentation is vital in e-commerce.
Distributed Marker Representation for Ambiguous Discourse Markers and Entangled Relations
Discourse analysis is an important task because it models intrinsic semantic structures between sentences in a document.
Efficiently Measuring the Cognitive Ability of LLMs: An Adaptive Testing Perspective
Different tests for different models using efficient adaptive testing -- we believe this has the potential to become a new norm in evaluating large language models.
Relation-Aware Diffusion Model for Controllable Poster Layout Generation
To advance research in this field, we have constructed a poster layout dataset named CGL-Dataset V2.
A Gradient-based Approach for Online Robust Deep Neural Network Training with Noisy Labels
In this paper, we propose a novel gradient-based approach to enable the detection of noisy labels for the online learning of model parameters, named Online Gradient-based Robust Selection (OGRS).
Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning
It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition.
Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding
To improve the convergence, a layer-by-layer distillation is applied to distill a quantized and tensor-compressed student model from a pre-trained transformer.
An AMR-based Link Prediction Approach for Document-level Event Argument Extraction
Motivated by the fact that all event structures can be inferred from AMR, this work reformulates EAE as a link prediction problem on AMR graphs.
Exploiting Abstract Meaning Representation for Open-Domain Question Answering
The Open-Domain Question Answering (ODQA) task involves retrieving and subsequently generating answers from fine-grained relevant passages within a database.
Evaluating Open-QA Evaluation
This study focuses on the evaluation of the Open Question Answering (Open-QA) task, which can directly estimate the factuality of large language models (LLMs).
Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations
Many techniques have been proposed to automatically generate SQL from natural language, but they suffer from two issues: (1) they still make many mistakes, particularly for complex queries, and (2) they do not provide a flexible way for non-expert users to validate and refine incorrect queries.
Masked Structural Growth for 2x Faster Language Model Pre-training
In terms of growth schedule, the impact of each single dimension on a schedule's efficiency is under-explored by existing work.
FlightBERT++: A Non-autoregressive Multi-Horizon Flight Trajectory Prediction Framework
Flight Trajectory Prediction (FTP) is an essential task in Air Traffic Control (ATC), which can assist air traffic controllers in managing airspace more safely and efficiently.
STM-UNet: An Efficient U-shaped Architecture Based on Swin Transformer and Multi-scale MLP for Medical Image Segmentation
Deep learning based models for medical image segmentation have made great progress in recent years.
VISAR: A Human-AI Argumentative Writing Assistant with Visual Programming and Rapid Draft Prototyping
In argumentative writing, writers must brainstorm hierarchical writing goals, ensure the persuasiveness of their arguments, and revise and organize their plans through drafting.
Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios
Multi-view clustering (MVC) aims at exploring category structures among multi-view data in self-supervised manners.
DeepMIM: Deep Supervision for Masked Image Modeling
Deep supervision, which involves extra supervisions to the intermediate features of a neural network, was widely used in image classification in the early deep learning era since it significantly reduces the training difficulty and eases the optimization like avoiding gradient vanish over the vanilla training.
Particle-based Online Bayesian Sampling
Online optimization has gained increasing interest due to its capability of tracking real-world streaming data.
DeepOHeat: Operator Learning-based Ultra-fast Thermal Simulation in 3D-IC Design
In this paper, for the first time, we propose DeepOHeat, a physics-aware operator learning framework to predict the temperature field of a family of heat equations with multiple parametric or non-parametric design configurations.
Side Adapter Network for Open-Vocabulary Semantic Segmentation
A side network is attached to a frozen CLIP model with two branches: one for predicting mask proposals, and the other for predicting attention bias which is applied in the CLIP model to recognize the class of masks.
PIFON-EPT: MR-Based Electrical Property Tomography Using Physics-Informed Fourier Networks
PIFON-EPT is the first method that can simultaneously reconstruct EP and transmit fields from incomplete noisy MR measurements, providing new opportunities for EPT research.
Tensorized Optical Multimodal Fusion Network
We propose the first tensorized optical multimodal fusion network architecture with a self-attention mechanism and low-rank tensor fusion.
Apples and Oranges? Assessing Image Quality over Content Recognition
A sequential spatial-channel attention module is proposed to simulate the visual attention and contrast sensitivity mechanisms that are crucial for content recognition and quality assessment.
FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
A key performance bottleneck when training graph neural network (GNN) models on large, real-world graphs is loading node features onto a GPU.
All in Tokens: Unifying Output Space of Visual Tasks via Soft Token
With these new techniques and other designs, we show that the proposed general-purpose task-solver can perform both instance segmentation and depth estimation well.
Ranked #14 on
Monocular Depth Estimation
on NYU-Depth V2
TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models
Our TinyMIM model of tiny size achieves 79. 6% top-1 accuracy on ImageNet-1K image classification, which sets a new record for small vision models of the same size and computation budget.
Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video Retrieval
During the knowledge distillation, an inheritance student branch is devised to absorb the knowledge from the teacher model.
Improving CLIP Fine-tuning Performance
Experiments suggest that the feature map distillation approach significantly boosts the fine-tuning performance of CLIP models on several typical downstream vision tasks.
DETR Does Not Need Multi-Scale or Locality Design
This paper presents an improved DETR detector that maintains a "plain" nature: using a single-scale feature map and global cross-attention calculations without specific locality constraints, in contrast to previous leading DETR-based detectors that reintroduce architectural inductive biases of multi-scale and locality into the decoder.
iCLIP: Bridging Image Classification and Contrastive Language-Image Pre-Training for Visual Recognition
This paper presents a method that effectively combines two prevalent visual recognition methods, i. e., image classification and contrastive language-image pre-training, dubbed iCLIP.
Refined Edge Usage of Graph Neural Networks for Edge Prediction
However, existing methods lack elaborate design regarding the distinctions between two tasks that have been frequently overlooked: (i) edges only constitute the topology in the node classification task but can be used as both the topology and the supervisions (i. e., labels) in the edge prediction task; (ii) the node classification makes prediction over each individual node, while the edge prediction is determinated by each pair of nodes.
EASpace: Enhanced Action Space for Policy Transfer
In this paper, a novel algorithm named EASpace (Enhanced Action Space) is proposed, which formulates macro actions in an alternative form to accelerate the learning process using multiple available sub-optimal expert policies.
CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detection
Recently, segmentation-based methods are quite popular in scene text detection, which mainly contain two steps: text kernel segmentation and expansion.
KPT: Keyword-guided Pre-training for Grounded Dialog Generation
For the former, the grounding knowledge consists of keywords extracted from the response.
ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format
Task-oriented dialogue (TOD) systems function as digital assistants, guiding users through various tasks such as booking flights or finding restaurants.
Exploring Discrete Diffusion Models for Image Captioning
The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one.
Could Giant Pretrained Image Models Extract Universal Representations?
In this paper, we present a study of frozen pretrained models when applied to diverse and representative computer vision tasks, including object detection, semantic segmentation and video action recognition.
Ranked #3 on
Action Recognition In Videos
on Kinetics-400
RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees
RLET iteratively performs single step reasoning with sentence selection and deduction generation modules, from which the training signal is accumulated across the tree with elaborately designed aligned reward function that is consistent with the evaluation.
DORE: Document Ordered Relation Extraction based on Generative Framework
In this paper, we investigate the root cause of the underwhelming performance of the existing generative DocRE models and discover that the culprit is the inadequacy of the training paradigm, instead of the capacities of the models.
Conversation Disentanglement with Bi-Level Contrastive Learning
Conversation disentanglement aims to group utterances into detached sessions, which is a fundamental task in processing multi-party conversations.
MR-Based Electrical Property Reconstruction Using Physics-Informed Neural Networks
Electrical properties (EP), namely permittivity and electric conductivity, dictate the interactions between electromagnetic waves and biological tissue.
Self-supervised Amodal Video Object Segmentation
The key intuition is that the occluded part of an object can be explained away if that part is visible in other frames, possibly deformed as long as the deformation can be reasonably learned.
Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning
Vision transformers have recently achieved competitive results across various vision tasks but still suffer from heavy computation costs when processing a large number of tokens.
Bridging the Gap to Real-World Object-Centric Learning
Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world.
Vega-MT: The JD Explore Academy Translation System for WMT22
As for model sizes, we scale the Transformer-Big up to the extremely large model that owns nearly 4. 7 Billion parameters, to fully enhance the model capacity for our Vega-MT.
Ranked #1 on
Machine Translation
on WMT 2022 English-Russian
Whole-Body Lesion Segmentation in 18F-FDG PET/CT
There has been growing research interest in using deep learning based method to achieve fully automated segmentation of lesion in Positron emission tomography computed tomography(PET CT) scans for the prognosis of various cancers.
An Empirical Study and Analysis of Learning Generalizable Manipulation Skill in the SAPIEN Simulator
This paper provides a brief overview of our submission to the no interaction track of SAPIEN ManiSkill Challenge 2021.
Structure Regularized Attentive Network for Automatic Femoral Head Necrosis Diagnosis and Localization
However, due to the tissue overlap, X-ray images are difficult to provide fine-grained features for early diagnosis.
Faint Features Tell: Automatic Vertebrae Fracture Screening Assisted by Contrastive Learning
Long-term vertebral fractures severely affect the life quality of patients, causing kyphotic, lumbar deformity and even paralysis.
CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation
Empathetic conversation is psychologically supposed to be the result of conscious alignment and interaction between the cognition and affection of empathy.
A Survey on Incomplete Multi-view Clustering
However, in practical applications, such as disease diagnosis, multimedia analysis, and recommendation system, it is common to observe that not all views of samples are available in many cases, which leads to the failure of the conventional multi-view clustering methods.
Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours
Text classification can be useful in many real-world scenarios, saving a lot of time for end users.
SHREC'22 Track: Sketch-Based 3D Shape Retrieval in the Wild
We define two SBSR tasks and construct two benchmarks consisting of more than 46, 000 CAD models, 1, 700 realistic models, and 145, 000 sketches in total.
Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification
It is a challenging and practical problem since the query images often suffer from resolution degradation due to the different capturing conditions from real-world cameras.
Domain Adaptive Nuclei Instance Segmentation and Classification via Category-aware Feature Alignment and Pseudo-labelling
In this work, we propose a novel deep neural network, namely Category-Aware feature alignment and Pseudo-Labelling Network (CAPL-Net) for UDA nuclei instance segmentation and classification.
TT-PINN: A Tensor-Compressed Neural PDE Solver for Edge Computing
Physics-informed neural networks (PINNs) have been increasingly employed due to their capability of modeling complex physics systems.
Self-Healing Robust Neural Networks via Closed-Loop Control
While numerous attack and defense techniques have been developed, this work investigates the robustness issue from a new angle: can we design a self-healing neural network that can automatically detect and fix the vulnerability issue by itself?
Learning Enhanced Representations for Tabular Data via Neighborhood Propagation
Prediction over tabular data is an essential and fundamental problem in many important downstream tasks.
On Data Scaling in Masked Image Modeling
Our study reveals that: (i) Masked image modeling is also demanding on larger data.
Predicting Electricity Infrastructure Induced Wildfire Risk in California
Our data include historical ignition and wire-down points triggered by grid infrastructure collected between 2015 to 2019 in Pacific Gas & Electricity territory along with various weather, vegetation, and very high resolution data on grid infrastructure including location, age, materials.
Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation
These properties, which we aggregately refer to as optimization friendliness, are identified and analyzed by a set of attention- and optimization-related diagnosis tools.
Ranked #2 on
Instance Segmentation
on COCO test-dev
(using extra training data)
Revealing the Dark Secrets of Masked Image Modeling
In this paper, we compare MIM with the long-dominant supervised pre-trained models from two perspectives, the visualizations and the experiments, to uncover their key representational differences.
Ranked #3 on
Depth Estimation
on NYU-Depth V2
Tensor Shape Search for Optimum Data Compression
Various tensor decomposition methods have been proposed for data compression.
Heterogeneous Information Network based Default Analysis on Banking Micro and Small Enterprise Users
Risk assessment is a substantial problem for financial institutions that has been extensively studied both for its methodological richness and its various practical applications.
Dialogue Meaning Representation for Task-Oriented Dialogue Systems
We propose Dialogue Meaning Representation (DMR), a pliable and easily extendable representation for task-oriented dialogue.
iCAR: Bridging Image Classification and Image-text Alignment for Visual Recognition
Second, we convert the image classification problem from learning parametric category classifier weights to learning a text encoder as a meta network to generate category classifier weights.
BLISS: Robust Sequence-to-Sequence Learning via Self-Supervised Input Representation
Data augmentations (DA) are the cores to achieving robust sequence-to-sequence learning on various natural language processing (NLP) tasks.
Visual Mechanisms Inspired Efficient Transformers for Image and Video Quality Assessment
Meanwhile, representative features for image quality perception in the spatial and frequency domains can also be derived from the IQA model, which are then fed into another windowed transformer architecture for video quality assessment (VQA).
Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension
Through benchmarking with QG models, we show that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions.
Ranked #1 on
Question Generation
on FairytaleQA
EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training
Large-scale pre-training has shown remarkable performance in building open-domain dialogue systems.
Multi-robot Cooperative Pursuit via Potential Field-Enhanced Reinforcement Learning
It is shown by numerical simulations that the proposed hybrid design outperforms the pursuit policies either learned from vanilla reinforcement learning or designed by the potential field method.
AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation
Applying this approach, we construct AugESC, an augmented dataset for the ESC task, which largely extends the scale and topic coverage of the crowdsourced ESConv corpus.
StoryBuddy: A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement
Despite its benefits for children's skill development and parent-child bonding, many parents do not often engage in interactive storytelling by having story-related dialogues with their child due to limited availability or challenges in coming up with appropriate questions.
Towards Collaborative Question Answering: A Preliminary Study
Knowledge and expertise in the real-world can be disjointedly owned.
Online, Informative MCMC Thinning with Kernelized Stein Discrepancy
A fundamental challenge in Bayesian inference is efficient representation of a target distribution.
A Critical Review of Inductive Logic Programming Techniques for Explainable AI
Despite recent advances in modern machine learning algorithms, the opaqueness of their underlying mechanisms continues to be an obstacle in adoption.
BIG-bench Machine Learning
Explainable artificial intelligence
+2
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model
However, semantic segmentation and the CLIP model perform on different visual granularity, that semantic segmentation processes on pixels while CLIP performs on images.
GRIN: Generative Relation and Intention Network for Multi-agent Trajectory Prediction
Learning the distribution of future trajectories conditioned on the past is a crucial problem for understanding multi-agent systems.
Representation Learning on Spatial Networks
Specifically, a provably information-lossless and roto-translation invariant representation of spatial information on networks is presented.
SimMIM: A Simple Framework for Masked Image Modeling
We also leverage this approach to facilitate the training of a 3B model (SwinV2-G), that by $40\times$ less data than that in previous practice, we achieve the state-of-the-art on four representative vision benchmarks.
Representation Learning
Self-Supervised Image Classification
+1
Swin Transformer V2: Scaling Up Capacity and Resolution
Three main techniques are proposed: 1) a residual-post-norm method combined with cosine attention to improve training stability; 2) A log-spaced continuous position bias method to effectively transfer models pre-trained using low-resolution images to downstream tasks with high-resolution inputs; 3) A self-supervised pre-training method, SimMIM, to reduce the needs of vast labeled images.
Ranked #4 on
Image Classification
on ImageNet V2
(using extra training data)
Bootstrap Your Object Detector via Mixed Training
We introduce MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free.
Why Propagate Alone? Parallel Use of Labels and Features on Graphs
In this regard, it has recently been proposed to use a randomly-selected portion of the training labels as GNN inputs, concatenated with the original node features for making predictions on the remaining labels.
Inductive Relation Prediction Using Analogy Subgraph Embeddings
Prevailing methods for relation prediction in heterogeneous graphs aim at learning latent representations (i. e., embeddings) of observed nodes and relations, and thus are limited to the transductive setting where the relation types must be known during training.
Kokoyi: Executable LaTeX for End-to-end Deep Learning
Despite substantial efforts from the deep learning system community to relieve researchers and practitioners from the burden of implementing models with ever-growing complexity, a considerable lingual gap remains between developing models in the language of mathematics and implementing them in the languages of computer.
It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books
Existing question answering (QA) techniques are created mainly to answer questions asked by humans.
Kinship Verification Based on Cross-Generation Feature Interaction Learning
Specifically, we take parents and children as a whole to extract the expressive local and non-local features.
Deep Collaborative Multi-Modal Learning for Unsupervised Kinship Estimation
To this end, we propose a novel deep collaborative multi-modal learning (DCML) to integrate the underlying information presented in facial properties in an adaptive manner to strengthen the facial details for effective unsupervised kinship verification.
EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training
Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue data and the model size compared with English ones.
TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation
Accurate segmentation of organs or lesions from medical images is crucial for reliable diagnosis of diseases and organ morphometry.
MConv: An Environment for Multimodal Conversational Search across Multiple Domains
Second, a set of benchmark results for dialogue state tracking, conversational recommendation, response generation as well as a unified model for multiple tasks are reported.
Ranked #2 on
Dialogue State Tracking
on MMConv
Learning Hierarchical Graph Neural Networks for Image Clustering
Our hierarchical GNN uses a novel approach to merge connected components predicted at each level of the hierarchy to form a new graph at the next level.
Context-Aware Attention-Based Data Augmentation for POI Recommendation
It aims at suggesting the next POI to a user in spatial and temporal context, which is a practical yet challenging task in various applications.
Video Swin Transformer
The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks.
Ranked #28 on
Action Classification
on Kinetics-600
(using extra training data)
End-to-End Semi-Supervised Object Detection with Soft Teacher
This paper presents an end-to-end semi-supervised object detection approach, in contrast to previous more complex multi-stage methods.
Ranked #6 on
Semi-Supervised Object Detection
on COCO 100% labeled data
(using extra training data)
DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation
To alleviate these problems, we propose a novel deep medical image segmentation framework called Dual Swin Transformer U-Net (DS-TransUNet), which might be the first attempt to concurrently incorporate the advantages of hierarchical Swin Transformer into both encoder and decoder of the standard U-shaped architecture to enhance the semantic segmentation quality of varying medical images.
A Unified Generative Framework for Aspect-Based Sentiment Analysis
Aspect-based Sentiment Analysis (ABSA) aims to identify the aspect terms, their corresponding sentiment polarities, and the opinion terms.
Ranked #1 on
Aspect Sentiment Triplet Extraction
on SemEval
Aspect-Based Sentiment Analysis
Aspect-oriented Opinion Extraction
+2
A Unified Generative Framework for Various NER Subtasks
To that end, we propose to formulate the NER subtasks as an entity span sequence generation task, which can be solved by a unified sequence-to-sequence (Seq2Seq) framework.
Ranked #10 on
Nested Named Entity Recognition
on GENIA
Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing
However, deep hashing networks are vulnerable to adversarial examples, which is a practical secure problem but seldom studied in hashing-based retrieval field.
Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning
Previous cycle-consistency correspondence learning methods usually leverage image patches for training.
3U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Acceleration
This paper emphasizes the importance and efficacy of training, quantization and accelerator design, and calls for more research breakthroughs in the area for AI on the edge.
Self-Supervised Learning with Swin Transformers
We are witnessing a modeling shift from CNN to Transformers in computer vision.
Ranked #75 on
Self-Supervised Image Classification
on ImageNet
Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections
However, the next word prediction training objective is still misaligned with the target zero-shot learning objective.
Group-Free 3D Object Detection via Transformers
Instead of grouping local points to each object candidate, our method computes the feature of an object from all the points in the point cloud with the help of an attention mechanism in the Transformers \cite{vaswani2017attention}, where the contribution of each point is automatically learned in the network training.
Ranked #3 on
3D Object Detection
on SUN-RGBD
High-Dimensional Uncertainty Quantification via Tensor Regression with Rank Determination and Adaptive Sampling
Recently, low-rank tensor methods have been developed to mitigate this issue, but two fundamental challenges remain open: how to automatically determine the tensor rank and how to adaptively pick the informative simulation samples.
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision.
Ranked #2 on
Image Classification
on OmniBenchmark
Bag of Tricks for Node Classification with Graph Neural Networks
Over the past few years, graph neural networks (GNN) and label propagation-based methods have made significant progress in addressing node classification tasks on graphs.
Ranked #1 on
Node Property Prediction
on ogbn-proteins
Graph Neural Networks Inspired by Classical Iterative Algorithms
Despite the recent success of graph neural networks (GNN), common architectures often exhibit significant limitations, including sensitivity to oversmoothing, long-range dependencies, and spurious edges, e. g., as can occur as a result of graph heterophily or adversarial attacks.
A Unified Framework for Specification Tests of Continuous Treatment Effect Models
We propose a general framework for the specification testing of continuous treatment effect models.
Bayesian Inference with Certifiable Adversarial Robustness
We consider adversarial training of deep neural networks through the lens of Bayesian learning, and present a principled framework for adversarial training of Bayesian Neural Networks (BNNs) with certifiable guarantees.
Towards Robust Neural Networks via Close-loop Control
We connect the robustness of neural networks with optimal control using the geometrical information of underlying data to design the control objective.
Semantics Disentangling for Generalized Zero-Shot Learning
Generalized zero-shot learning (GZSL) aims to classify samples under the assumption that some classes are not observable during training.
Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning
To address these issues, in this paper, we propose a novel framework that leverages dual variational autoencoders with a triplet loss to learn discriminative latent features and applies the entropy-based calibration to minimize the uncertainty in the overlapped area between the seen and unseen classes.
Explore with Dynamic Map: Graph Structured Reinforcement Learning
In reinforcement learning, a map with states and transitions built based on historical trajectories is often helpful in exploration and exploitation.
Composite Adversarial Training for Multiple Adversarial Perturbations and Beyond
One intriguing property of deep neural networks (DNNs) is their vulnerability to adversarial perturbations.
Leveraging Batch Normalization for Vision Transformers
Transformer-based vision architectures have attracted great attention because of the strong performance over the convolutional neural networks (CNNs).
Active Sampling for Accelerated MRI with Low-Rank Tensors
In this paper, we introduce an active low-rank tensor model for fast MR imaging.
TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors
To bridge this gap, we design and implement TROJANZOO, the first open-source platform for evaluating neural backdoor attacks/defenses in a unified, holistic, and practical manner.
Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings
Cycle-consistent training is widely used for jointly learning a forward and inverse mapping between two domains of interest without the cumbersome requirement of collecting matched pairs within each domain.
GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation
With a human-annotated test set, we provide this new benchmark dataset for future research on unsupervised text generation from knowledge graphs.
Ranked #1 on
Unsupervised KG-to-Text Generation
on GenWiki (Fine)
GraphHINGE: Learning Interaction Models of Structured Neighborhood on Heterogeneous Information Network
Heterogeneous information network (HIN) has been widely used to characterize entities of various types and their complex relations.
Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
We argue that the power of contrastive learning has yet to be fully unleashed, as current methods are trained only on instance-level pretext tasks, leading to representations that may be sub-optimal for downstream tasks requiring dense pixel predictions.
Overview of the Ninth Dialog System Technology Challenge: DSTC9
Interactive evaluation of dialog, and 4.
Towards Compact Neural Networks via End-to-End Training: A Bayesian Tensor Approach with Automatic Rank Determination
This paper presents a novel end-to-end framework for low-rank tensorized training of neural networks.
DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs
To minimize the overheads associated with distributed computations, DistDGL uses a high-quality and light-weight min-cut graph partitioning algorithm along with multiple balancing constraints.
CoLAKE: Contextualized Language and Knowledge Embedding
With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of these models.
Causal Inference of General Treatment Effects using Neural Networks with A Diverging Number of Confounders
This paper considers a generalized optimization framework for efficient estimation of general treatment effects using artificial neural networks (ANNs) to approximate the unknown nuisance function of growing-dimensional confounders.
Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior
Nonnegative matrix factorization is usually powerful for learning the "shallow" parts-based representation, but it clearly fails to discover deep hierarchical information within both the basis and representation spaces.
FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems
FeatGraph provides a flexible programming interface to express diverse GNN models by composing coarse-grained sparse templates with fine-grained user-defined functions (UDFs) on each vertex/edge.
Trojaning Language Models for Fun and Profit
Recent years have witnessed the emergence of a new paradigm of building natural language processing (NLP) systems: general-purpose, pre-trained language models (LMs) are composed with simple downstream models and fine-tuned for a variety of NLP tasks.
Adversarial Bipartite Graph Learning for Video Domain Adaptation
To further enhance the model capacity and testify the robustness of the proposed architecture on difficult transfer tasks, we extend our model to work in a semi-supervised setting using an additional video-level bipartite graph.
Ranked #2 on
Domain Adaptation
on HMDB --> UCF (full)
RepPoints V2: Verification Meets Regression for Object Detection
Though RepPoints provides high performance, we find that its heavy reliance on regression for object localization leaves room for improvement.
Ranked #27 on
Object Detection
on COCO-O
A Closer Look at Local Aggregation Operators in Point Cloud Analysis
Our investigation reveals that despite the different designs of these operators, all of these operators make surprisingly similar contributions to the network performance under the same network input and feature numbers and result in the state-of-the-art accuracy on standard benchmarks.
Ranked #4 on
3D Semantic Segmentation
on PartNet
An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph
To the best of our knowledge, this is the first work providing an efficient neighborhood-based interaction model in the HIN-based recommendations.
Parametric Instance Classification for Unsupervised Visual Feature Learning
This paper presents parametric instance classification (PIC) for unsupervised visual feature learning.
Disentangled Non-Local Neural Networks
This paper first studies the non-local block in depth, where we find that its attention computation can be split into two terms, a whitened pairwise term accounting for the relationship between two pixels and a unary term representing the saliency of every pixel.
Ranked #20 on
Semantic Segmentation
on Cityscapes test
(using extra training data)
Dual-level Semantic Transfer Deep Hashing for Efficient Social Image Retrieval
Specifically, we design a complementary dual-level semantic transfer mechanism to efficiently discover the potential semantics of tags and seamlessly transfer them into binary hash codes.
CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training
Due to the difficulty and high cost of data collection, the supervised data available in the two fields are usually on the magnitude of tens of thousands, for example, 18K in the WebNLG~2017 dataset after preprocessing, which is far fewer than the millions of data for other tasks such as machine translation.
Relation of the Relations: A New Paradigm of the Relation Extraction Problem
In natural language, often multiple entities appear in the same text.
Repurpose Open Data to Discover Therapeutics for COVID-19 using Deep Learning
While this study, by no means recommends specific drugs, it demonstrates a powerful deep learning methodology to prioritize existing drugs for further investigation, which holds the potential of accelerating therapeutic development for COVID-19.
Learning Goal-oriented Dialogue Policy with Opposite Agent Awareness
Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treat the opposite agent policy as part of the environment.
