Search Results for author:
Found 36 papers, 16 papers with code
Energy-Aware Analog Aggregation for Federated Learning with Redundant Data
In this work, we consider analog aggregation to scale down the communication cost with respect to the number of workers, and introduce data redundancy to the system to deal with non-i. i. d.
ROI Pooled Correlation Filters for Visual Tracking
The ROI (region-of-interest) based pooling method performs pooling operations on the cropped ROI regions for various samples and has shown great success in the object detection methods.
RIVA: A Pre-trained Tweet Multimodal Model Based on Text-image Relation for Multimodal NER
In the multimodal NER task, the experimental results show the significance of text-related visual features for the visual-linguistic model and our approach achieves SOTA performance on the MNER datasets.
droidlet: modular, heterogenous, multi-modal agents
In recent years, there have been significant advances in building end-to-end Machine Learning (ML) systems that learn at scale.
Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraints
In this work, we consider an over-the-air FEEL system with analog gradient aggregation, and propose an energy-aware dynamic device scheduling algorithm to optimize the training performance under energy constraints of devices, where both communication energy for gradient aggregation and computation energy for local training are included.
NTIRE 2021 Multi-modal Aerial View Object Classification Challenge
In this paper, we introduce the first Challenge on Multi-modal Aerial View Object Classification (MAVOC) in conjunction with the NTIRE 2021 workshop at CVPR.
Coded Computation across Shared Heterogeneous Workers with Communication Delay
In this work, we consider a multi-master heterogeneous-worker distributed computing scenario, where multiple matrix multiplication tasks are encoded and allocated to workers for parallel computation.
NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment
Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provided natural language instructions.
Online V2X Scheduling for Raw-Level Cooperative Perception
Cooperative perception of connected vehicles comes to the rescue when the field of view restricts stand-alone intelligence.
Time-Correlated Sparsification for Efficient Over-the-Air Model Aggregation in Wireless Federated Learning
In this work, we propose time-correlated sparsification with hybrid aggregation (TCS-H) for communication-efficient FEEL, which exploits jointly the power of model compression and over-the-air computation.
Many Episode Learning in a Modular Embodied Agent via End-to-End Interaction
In this work we give a case study of an embodied machine-learning (ML) powered agent that improves itself via interactions with crowd-workers.
Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021
The primary goal of the competition is to approach the problem of how to build interactive agents that learn to solve a task while provided with grounded natural language instructions in a collaborative environment.
IGLU 2022: Interactive Grounded Language Understanding in a Collaborative Environment at NeurIPS 2022
Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provided natural language instructions.
Benchmarking the Robustness of Deep Neural Networks to Common Corruptions in Digital Pathology
Evaluated on two resulting benchmark datasets, we find that (1) a variety of deep neural network models suffer from a significant accuracy decrease (double the error on clean images) and the unreliable confidence estimation on corrupted images; (2) A low correlation between the validation and test errors while replacing the validation set with our benchmark can increase the correlation.
DOLPHINS: Dataset for Collaborative Perception enabled Harmonious and Interconnected Self-driving
In this work, we release DOLPHINS: Dataset for cOllaborative Perception enabled Harmonious and INterconnected Self-driving, as a new simulated large-scale various-scenario multi-view multi-modality autonomous driving dataset, which provides a ground-breaking benchmark platform for interconnected autonomous driving.
Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised Object Detection
Instead of directly exploiting the pseudo labels produced by the teacher detector, we take the first attempt at reducing their deviation from ground truth using dual polishing learning, where two differently structured polishing networks are elaborately developed and trained using synthesized paired pseudo labels and the corresponding ground truth for categories and bounding boxes on the given annotated objects, respectively.
Ranked #10 on
Semi-Supervised Object Detection
on COCO 5% labeled data
MEET: Mobility-Enhanced Edge inTelligence for Smart and Green 6G Networks
Accordingly, base stations (BSs) and edge servers (ESs) need to be densely deployed, leading to huge deployment and operation costs, in particular the energy costs.
Collecting Interactive Multi-modal Datasets for Grounded Language Understanding
Human intelligence can remarkably adapt quickly to new tasks and environments.
MOB-FL: Mobility-Aware Federated Learning for Intelligent Connected Vehicles
Federated learning (FL) is a promising approach to enable the future Internet of vehicles consisting of intelligent connected vehicles (ICVs) with powerful sensing, computing and communication capabilities.
MASS: Mobility-Aware Sensor Scheduling of Cooperative Perception for Connected Automated Driving
Specifically, we design a mobility-aware sensor scheduling (MASS) algorithm based on the restless multi-armed bandit (RMAB) theory to maximize the expected average perception gain.
Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classification
Our framework is evaluated on five pathology WSI datasets on various WSI heads.
Transforming Human-Centered AI Collaboration: Redefining Embodied Agents Capabilities through Interactive Grounded Language Instructions
Human intelligence's adaptability is remarkable, allowing us to adjust to new tasks and multi-modal environments swiftly.
Digital-SC: Digital Semantic Communication with Adaptive Network Split and Learned Non-Linear Quantization
Additionally, structured pruning is incorporated to reduce the dimension of the transmitted features.
PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of Pathology
Secondly, by leveraging the collected data, we construct PathCLIP, a pathology-dedicated CLIP, to enhance PathAsst's capabilities in interpreting pathology images.
Data-Heterogeneous Hierarchical Federated Learning with Mobility
Federated learning enables distributed training of machine learning (ML) models across multiple devices in a privacy-preserving manner.
Masked conditional variational autoencoders for chromosome straightening
This yields a non-trivial reconstruction task, allowing the model to effectively preserve chromosome banding patterns and structure details in the reconstructed results.
A Data Source for Reasoning Embodied Agents
In this work, to further pursue these advances, we introduce a new data generator for machine reasoning that integrates with an embodied agent.
Multimodal Question Answering for Unified Information Extraction
In addition, the effectiveness of our framework can successfully transfer to the few-shot setting, enhancing LMMs on a scale of 10B parameters to be competitive or outperform much larger language models such as ChatGPT and GPT-4.
Attention-Challenging Multiple Instance Learning for Whole Slide Image Classification
Overfitting is a significant challenge in the application of Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) analysis.
Test-Time Training for Semantic Segmentation with Output Contrastive Loss
Although deep learning-based segmentation models have achieved impressive performance on public benchmarks, generalizing well to unseen environments remains a major challenge.
Unleashing the Power of Prompt-driven Nucleus Instance Segmentation
In this paper, we present a novel prompt-driven framework that consists of a nucleus prompter and SAM for automatic nucleus instance segmentation.
MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning.
MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following
In the realm of large language models (LLMs), enhancing instruction-following capability often involves curating expansive training data.
Benchmarking PathCLIP for Pathology Image Analysis
Additionally, we assess the robustness of PathCLIP in the task of image-image retrieval, revealing that PathCLIP performs less effectively than PLIP on Osteosarcoma but performs better on WSSS4LUAD under diverse corruptions.
Mobility Accelerates Learning: Convergence Analysis on Hierarchical Federated Learning in Vehicular Networks
Hierarchical federated learning (HFL) enables distributed training of models across multiple devices with the help of several edge servers and a cloud edge server in a privacy-preserving manner.
PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology
To address this, we introduce PathMMU, the largest and highest-quality expert-validated pathology benchmark for Large Multimodal Models (LMMs).
