Search Results for author:
Found 80 papers, 20 papers with code
Incremental Few-Shot Meta-Learning via Indirect Discriminant Alignment
This process enables incrementally improving the model by processing multiple learning episodes, each representing a different learning task, even with few training examples.
LLM-based HSE Compliance Assessment: Benchmark, Performance, and Advancements
Health, Safety, and Environment (HSE) compliance assessment demands dynamic real-time decision-making under complicated regulations and complex human-machine-environment interactions.
M-learner:A Flexible And Powerful Framework To Study Heterogeneous Treatment Effect In Mediation Model
We propose a novel method, termed the M-learner, for estimating heterogeneous indirect and total treatment effects and identifying relevant subgroups within a mediation framework.
TelePlanNet: An AI-Driven Framework for Efficient Telecom Network Planning
The selection of base station sites is a critical challenge in 5G network planning, which requires efficient optimization of coverage, cost, user satisfaction, and practical constraints.
Enhancing Facial Privacy Protection via Weakening Diffusion Purification
The rapid growth of social media has led to the widespread sharing of individual portrait images, which pose serious privacy risks due to the capabilities of automatic face recognition (AFR) systems for mass surveillance.
ObjectMover: Generative Object Movement with Video Prior
Simple as it seems, moving an object to another location within an image is, in fact, a challenging image-editing task that requires re-harmonizing the lighting, adjusting the pose based on perspective, accurately filling occluded regions, and ensuring coherent synchronization of shadows and reflections while maintaining the object identity.
Fusion of Various Optimization Based Feature Smoothing Methods for Wearable and Non-invasive Blood Glucose Estimation
If the accumulate probability of any selected optimization method at a point is greater than a threshold value, then the accumulate probabilities of these three selected optimization methods at that point are reset to zero.
Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation Framework
Multimodal Retrieval-Augmented Generation (MRAG) enhances reasoning capabilities by integrating external knowledge.
Glioma Multimodal MRI Analysis System for Tumor Layered Diagnosis via Multi-task Semi-supervised Learning
Gliomas are the most common primary tumors of the central nervous system.
Generative Video Propagation
Large-scale video generation models have the inherent ability to realistically model natural scenes.
UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics
We introduce UniReal, a unified framework designed to address various image generation and editing tasks.
LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors
In this paper, we propose a novel image generation pipeline based on Latent Diffusion Models (LDMs) that generates images with two layers: a foreground layer (RGBA) with transparency information and a background layer (RGB).
Generative Image Layer Decomposition with Visual Effects
Layered representations, which allow for independent editing of image components, are essential for user-driven content creation, yet existing approaches often struggle to decompose image into plausible layers with accurately retained transparent visual effects such as shadows and reflections.
FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity
To support this endeavor, we introduce COMPOSITIONCAP, a new dataset for multi-grained region compositional image captioning, which introduces the task of compositional attribute-aware regional image captioning.
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction
Existing feedforward image-to-3D methods mainly rely on 2D multi-view diffusion models that cannot guarantee 3D consistency.
HRDecoder: High-Resolution Decoder Network for Fundus Image Lesion Segmentation
Our method effectively improves the overall segmentation accuracy of fundus lesions while consuming reasonable memory and computational overhead, and maintaining satisfying inference speed.
Analyzing Nobel Prize Literature with Large Language Models
This study examines the capabilities of advanced Large Language Models (LLMs), particularly the o1 model, in the context of literary analysis.
Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning
In order to improve the efficiency, PoG prunes irrelevant information from the graph exploration first and introduces efficient three-step pruning techniques that incorporate graph structures, LLM prompting, and a pre-trained language model (e. g., SBERT) to effectively narrow down the explored candidate paths.
Ranked #1 on
Knowledge Base Question Answering
on ComplexWebQuestions
(EM metric)
GroupDiff: Diffusion-based Group Portrait Editing
The training data engine covers the diverse needs of group portrait editing.
DuA: Dual Attentive Transformer in Long-Term Continuous EEG Emotion Analysis
To address this issue, we propose a Dual Attentive (DuA) transformer framework for long-term continuous EEG emotion analysis.
What If We Recaption Billions of Web Images with LLaMA-3?
For discriminative models like CLIP, we observe enhanced zero-shot performance in cross-modal retrieval tasks.
Ranked #127 on
Visual Question Answering
on MM-Vet
Object-level Scene Deocclusion
Deoccluding the hidden portions of objects in a scene is a formidable task, particularly when addressing real-world scenes.
The current status of large language models in summarizing radiology report impressions
Besides the automatic quantitative evaluation metrics, we define five human evaluation metrics, i. e., completeness, correctness, conciseness, verisimilitude, and replaceability, to evaluate the semantics of the generated impressions.
SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editing
Compared with existing methods for personalized subject swapping, SwapAnything has three unique advantages: (1) precise control of arbitrary objects and parts rather than the main subject, (2) more faithful preservation of context pixels, (3) better adaptation of the personalized concept to the image.
MGARD: A multigrid framework for high-performance, error-controlled data compression and refactoring
We describe MGARD, a software providing MultiGrid Adaptive Reduction for floating-point scientific data on structured and unstructured grids.
UniHuman: A Unified Model for Editing Human Images in the Wild
In this paper, we propose UniHuman, a unified model that addresses multiple facets of human image editing in real-world settings.
SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout Control
To overcome these limitations, we introduce SmartMask, which allows any novice user to create detailed masks for precise object insertion.
SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis
On the highly competitive ADE20K and COCO benchmarks, our data generation method markedly improves the performance of state-of-the-art segmentation models in semantic segmentation, panoptic segmentation, and instance segmentation.
Perceptual Artifacts Localization for Image Synthesis Tasks
Recent advancements in deep generative models have facilitated the creation of photo-realistic images across various tasks.
Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modals
Inspired by this, this paper innovatively proposes a multimodal Hypergraph-of-Thought (HoT) reasoning paradigm, which enables the foundation models to possess the expert-level ability of high-order multi-hop reasoning and multimodal comparative judgement.
Towards Open-World Segmentation of Parts
Second, we introduce a novel approach to improve part segmentation on unseen objects, inspired by an interesting finding -- for unseen objects, the pixel-wise features extracted by the model often reveal high-quality part segments.
Crowd Counting with Sparse Annotation
This paper presents a new annotation method called Sparse Annotation (SA) for crowd counting, which reduces human labeling efforts by sparsely labeling individuals in an image.
SparDL: Distributed Deep Learning Training with Efficient Sparse Communication
Recently, a few methods have been put forward to handle the SGA dilemma.
TOT: Topology-Aware Optimal Transport For Multimodal Hate Detection
Multimodal hate detection, which aims to identify harmful content online such as memes, is crucial for building a wholesome internet environment.
HierCat: Hierarchical Query Categorization from Weakly Supervised Data at Facebook Marketplace
Query categorization at customer-to-customer e-commerce platforms like Facebook Marketplace is challenging due to the vagueness of search intent, noise in real-world data, and imbalanced training data across languages.
OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization
To this end, we create OPT-IML Bench: a large benchmark for Instruction Meta-Learning (IML) of 2000 NLP tasks consolidated into task categories from 8 existing benchmarks, and prepare an evaluation framework to measure three types of model generalizations: to tasks from fully held-out categories, to held-out tasks from seen categories, and to held-out instances from seen tasks.
Ranked #26 on
Natural Language Inference
on RTE
Structure-Guided Image Completion with Image-level and Object-level Semantic Discriminators
Moreover, the object-level discriminators take aligned instances as inputs to enforce the realism of individual objects.
SceneComposer: Any-Level Semantic Image Synthesis
We propose a new framework for conditional image synthesis from semantic layouts of any precision levels, ranging from pure text to a 2D semantic canvas with precise shapes.
A Light-weight, Effective and Efficient Model for Label Aggregation in Crowdsourcing
Due to the dynamic nature, the proposed algorithms can also estimate true labels online without re-visiting historical data.
Proceedings of Principle and practice of data and Knowledge Acquisition Workshop 2022 (PKAW 2022)
Over the past two decades, PKAW has provided a forum for researchers and practitioners to discuss the state-of-the-arts in the area of knowledge acquisition and machine intelligence (MI, also Artificial Intelligence, AI).
Exploring Contextual Relationships for Cervical Abnormal Cell Detection
To mimic these behaviors, we propose to explore contextual relationships to boost the performance of cervical abnormal cell detection.
Recent Advances for Quantum Neural Networks in Generative Learning
Due to the intrinsic probabilistic nature of quantum mechanics, it is reasonable to postulate that quantum generative learning models (QGLMs) may surpass their classical counterparts.
Few-shot Named Entity Recognition with Self-describing Networks
In this paper, we propose a self-describing mechanism for few-shot NER, which can effectively leverage illustrative instances and precisely transfer knowledge from external resources by describing both entity types and mentions using a universal concept set.
Unified Structure Generation for Universal Information Extraction
Information extraction suffers from its varying targets, heterogeneous structures, and demand-specific schemas.
Ranked #5 on
Aspect-Based Sentiment Analysis (ABSA)
on ASTE
(using extra training data)
Uncovering the System Vulnerability and Criticality of Human Brain under Dynamical Neuropathological Events in Alzheimer's Disease
Background: Despite the striking efforts in investigating neurobiological factors behind the acquisition of amyloid-\b{eta} (A), protein tau (T), and neurodegeneration ([N]) biomarkers, the mechanistic pathways of how AT[N] biomarkers spreading throughout the brain remain elusive.
Deep Open Set Identification for RF Devices
Artificial intelligence (AI) based device identification improves the security of the internet of things (IoT), and accelerates the authentication process.
M2MRF: Many-to-Many Reassembly of Features for Tiny Lesion Segmentation in Fundus Images
It reassembles features in a dimension-reduced feature space and simultaneously aggregates multiple features inside a large predefined region into multiple target features.
A Light-weight Interpretable Compositional Model for Nuclei Detection and Weakly-Supervised Segmentation
It only requires annotations on isolated nucleus, rather than on all nuclei in the dataset.
Context-aware Reranking with Utility Maximization for Recommendation
As a critical task for large-scale commercial recommender systems, reranking has shown the potential of improving recommendation results by uncovering mutual influence among items.
Fine-grained Entity Typing via Label Reasoning
Conventional entity typing approaches are based on independent classification paradigms, which make them difficult to recognize inter-dependent, long-tailed and fine-grained entity types.
Ranked #8 on
Entity Typing
on Open Entity
Modeling time evolving COVID-19 uncertainties with density dependent asymptomatic infections and social reinforcement
Different from existing COVID-19 models, SUDR characterizes the undocumented infections during unknown transmission processes.
AutoFT: Automatic Fine-Tune for Parameters Transfer Learning in Click-Through Rate Prediction
The field-wise transfer policy decides how the pre-trained embedding representations are frozen or fine-tuned based on the given instance from the target domain.
Visual analogy: Deep learning versus compositional models
We compared human performance to that of two recent deep learning models (Siamese Network and Relation Network) directly trained to solve these analogy problems, as well as to that of a compositional model that assesses relational similarity between part-based representations.
Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems
Finally, we evaluate our system using a typical movie ticket booking task and show that the dialogue simulator is an essential component of the system that leads to over $50\%$ improvement in turn-level action signature prediction accuracy.
COVID-19 Modeling: A Review
The SARS-CoV-2 virus and COVID-19 disease have posed unprecedented and overwhelming demand, challenges and opportunities to domain, model and data driven modeling.
Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles
We believe our dataset provides a rich testbed to study UDA for part segmentation and will help to significantly push forward research in this area.
Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency
However, existing approaches which rely only on image-level class labels predominantly suffer from errors due to (a) partial segmentation of objects and (b) missing object predictions.
Analyzing the Spatiotemporal Interaction and Propagation of ATN Biomarkers in Alzheimer's Disease using Longitudinal Neuroimaging Data
Three major biomarkers: beta-amyloid (A), pathologic tau (T), and neurodegeneration (N), are recognized as valid proxies for neuropathologic changes of Alzheimer's disease.
Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification
The approach also applies a semi-supervised learning process to re-train knowledge-to-visual model.
Cross Knowledge-based Generative Zero-Shot Learning Approach with Taxonomy Regularization
CKL enables more relevant semantic features to be trained for semantic-to-visual feature embedding in ZSL, while Taxonomy Regularization (TR) significantly improves the intersections with unseen images with more generalized visual features generated from generative network.
A Deep Retinal Image Quality Assessment Network with Salient Structure Priors
Dual-branch SalStructIQA contains two CNN branches and one is guided by large-size salient structures while the other is guided by tiny-size salient structures.
Dual-Branch Network with Dual-Sampling Modulated Dice Loss for Hard Exudate Segmentation from Colour Fundus Images
In detail, for the first branch, we use a uniform sampler to sample pixels from predicted segmentation mask for Dice loss calculation, which leads to this branch naturally be biased in favour of large hard exudates as Dice loss generates larger cost on misidentification of large hard exudates than small hard exudates.
U-rank: Utility-oriented Learning to Rank with Implicit Feedback
To this end, we propose a novel ranking framework called U-rank that directly optimizes the expected utility of the ranking list.
A Dark and Bright Channel Prior Guided Deep Network for Retinal Image Quality Assessment
Retinal image quality assessment is an essential task in the diagnosis of retinal diseases.
Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion
The structure of the compositional model enables CompositionalNets to decompose images into objects and context, as well as to further decompose object representations in terms of individual parts and the objects' pose.
ADIOS 2: The Adaptable Input Output System. A framework for high-performance data management
We present ADIOS 2, the latest version of the Adaptable Input Output (I/O) System.
Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion
Inspired by the success of compositional models at classifying partially occluded objects, we propose to integrate compositional models and DCNNs into a unified deep model with innate robustness to partial occlusion.
Incremental Meta-Learning via Indirect Discriminant Alignment
Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a generic representation by solving multiple few-shot tasks sampled from a large dataset and a testing phase, where the meta-learner leverages its learnt internal representation for a specific few-shot task involving classes which were not seen during the meta-training phase.
Localizing Occluders with Compositional Convolutional Networks
Our experimental results demonstrate that the proposed extensions increase the model's performance at localizing occluders as well as at classifying partially occluded objects.
A Deep Gradient Boosting Network for Optic Disc and Cup Segmentation
To build connections among prediction branches, this paper introduces gradient boosting framework to deep classification model and proposes a gradient boosting network called BoostNet.
Dual-attention Focused Module for Weakly Supervised Object Localization
In each branch, the input feature map is deduced into an enhancement map and a mask map, thereby highlighting the most discriminative parts or hiding them.
Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion
In this work, we combine DCNNs and compositional object models to retain the best of both approaches: a discriminative model that is robust to partial occlusion and mask attacks.
DDNet: Cartesian-polar Dual-domain Network for the Joint Optic Disc and Cup Segmentation
In this paper, we propose a novel segmentation approach, named Cartesian-polar dual-domain network (DDNet), which for the first time considers the complementary of the Cartesian domain and the polar domain.
Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval
Sketch-based image retrieval (SBIR) is widely recognized as an important vision problem which implies a wide range of real-world applications.
Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
In the second iteration of the competition in 2018, university teams advanced the state of the art by using context in dialog models, leveraging knowledge graphs for language understanding, handling complex utterances, building statistical and hierarchical dialog managers, and leveraging model-driven signals from user responses.
Semantic Part Detection via Matching: Learning to Generalize to Novel Viewpoints from Limited Training Data
In particular, this enables images in the training dataset to be matched to a virtual 3D model of the object (for simplicity, we assume that the object viewpoint can be estimated by standard techniques).
Comparison-Based Convolutional Neural Networks for Cervical Cell/Clumps Detection in the Limited Data Scenario
In this paper we propose an efficient CNN-based object detection methods for cervical cancer cells/clumps detection.
Conversational AI: The Science Behind the Alexa Prize
This paper outlines the advances created by the university teams as well as the Alexa Prize team to achieve the common goal of solving the problem of Conversational
Unleashing the Potential of CNNs for Interpretable Few-Shot Learning
Our models are based on the idea of encoding objects in terms of visual concepts, which are interpretable visual cues represented by the feature vectors within CNNs.
Few-shot Learning by Exploiting Visual Concepts within CNNs
In this work, we address these limitations of CNNs by developing novel, flexible, and interpretable models for few-shot learning.
