Search Results for author:
Found 62 papers, 24 papers with code
SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer
Despite this progress, mask strategy still suffers from two inherent limitations: (a) training-inference discrepancy and (b) fuzzy relations between mask reconstruction & generative diffusion process, resulting in sub-optimal training of DiT.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we present the latest model of the Gemini family, Gemini 1. 5 Pro, a highly compute-efficient multimodal mixture-of-experts model capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
Ranked #20 on
Code Generation
on HumanEval
DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training
DPAdapter modifies and enhances the sharpness-aware minimization (SAM) technique, utilizing a two-batch strategy to provide a more accurate perturbation estimate and an efficient gradient descent, thereby improving parameter robustness against noise.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Multi-task Language Understanding
on MMLU
(using extra training data)
DSR-Diff: Depth Map Super-Resolution with Diffusion Model
Color-guided depth map super-resolution (CDSR) improve the spatial resolution of a low-quality depth map with the corresponding high-quality color map, benefiting various applications such as 3D reconstruction, virtual reality, and augmented reality.
The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks
In the attack, one can construct a PII association task, whereby an LLM is fine-tuned using a minuscule PII dataset, to potentially reinstate and reveal concealed PIIs.
Business Process Text Sketch Automation Generation Using Large Language Model
Business process document generation is a crucial stage in BPM.
On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence
In this work, we explore the promises and challenges of developing multimodal foundation models for GeoAI.
Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation
Inverse path tracing has recently been applied to joint material and lighting estimation, given geometry and multi-view HDR observations of an indoor scene.
EVKG: An Interlinked and Interoperable Electric Vehicle Knowledge Graph for Smart Transportation System
Over the past decade, the electric vehicle industry has experienced unprecedented growth and diversification, resulting in a complex ecosystem.
Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
Finally, we perform both theoretical and experimental analysis, showing that the GRASP enhancement does not reduce the effectiveness of the stealthy attacks against the backdoor detection methods based on weight analysis, as well as other backdoor mitigation methods without using detection.
Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models
Our idea is to retrain a given DNN model on randomly labeled clean data, to induce a CF on the model, leading to a sudden forget on both primary and backdoor tasks; then we recover the primary task by retraining the randomized model on correctly labeled clean data.
Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback
Here we demonstrate how to use reinforcement learning from human feedback (RLHF) to improve upon simulated, embodied agents trained to a base level of competency with imitation learning.
Understanding Impacts of Task Similarity on Backdoor Attack and Detection
With extensive studies on backdoor attack and detection, still fundamental questions are left unanswered regarding the limits in the adversary's capability to attack and the defender's capability to detect.
Towards General-Purpose Representation Learning of Polygonal Geometries
For the spatial domain approach, we propose ResNet1D, a 1D CNN-based polygon encoder, which uses circular padding to achieve loop origin invariance on simple polygons.
PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes
Most indoor 3D scene reconstruction methods focus on recovering 3D geometry and scene layout.
IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes
Indoor scenes exhibit significant appearance variations due to myriad interactions between arbitrarily diverse object shapes, spatially-changing materials, and complex lighting.
Physically-Based Editing of Indoor Scene Lighting from a Single Image
We tackle this problem using two novel components: 1) a holistic scene reconstruction method that estimates scene reflectance and parametric 3D lighting, and 2) a neural rendering framework that re-renders the scene from our predictions.
A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning
Gradient-based Meta-RL (GMRL) refers to methods that maintain two-level optimisation procedures wherein the outer-loop meta-learner guides the inner-loop gradient-based reinforcement learner to achieve fast adaptations.
Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning
A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language.
Narrative Cartography with Knowledge Graphs
With the help of this tool, the retrieved data from KGs are directly materialized in a GIS format which is ready for spatial analysis and mapping.
Time in a Box: Advancing Knowledge Graph Completion with Temporal Scopes
Hence, knowledge base completion (KBC) on temporal knowledge bases (TKB), where each statement \textit{may} be associated with a temporal scope, has attracted growing attention.
A Review of Location Encoding for GeoAI: Methods and Applications
A common need for artificial intelligence models in the broader geoscience is to represent and encode various types of spatial data, such as points (e. g., points of interest), polylines (e. g., trajectories), polygons (e. g., administrative regions), graphs (e. g., transportation networks), or rasters (e. g., remote sensing images), in a hidden embedding space so that they can be readily incorporated into deep learning models.
Improving Contrastive Learning by Visualizing Feature Transformation
To our knowledge, this is the first attempt of its kind.
OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets
Finally, we demonstrate that our framework may also be integrated with physics engines, to create virtual robotics environments with unique ground truth such as friction coefficients and correspondence to real scenes.
Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directions
As an important part of Artificial Intelligence (AI), Question Answering (QA) aims at generating answers to questions phrased in natural language.
Boosting Semi-Supervised Face Recognition with Noise Robustness
This paper presents an effective solution to semi-supervised face recognition that is robust to the label noise aroused by the auto-labelling.
Robust Classification via Support Vector Machines
Classification models are very sensitive to data uncertainty, and finding robust classifiers that are less sensitive to data uncertainty has raised great interest in the machine learning literature.
Imitating Interactive Intelligence
These evaluations convincingly demonstrate that interactive training and auxiliary losses improve agent behaviour beyond what is achieved by supervised learning of actions alone.
Generalization Bound of Gradient Descent for Non-Convex Metric Learning
Metric learning aims to learn a distance measure that can benefit distance-based methods such as the nearest neighbour (NN) classifier.
Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints
Estimating relative camera poses from consecutive frames is a fundamental problem in visual odometry (VO) and simultaneous localization and mapping (SLAM), where classic methods consisting of hand-crafted features and sampling-based outlier rejection have been a dominant choice for over a decade.
OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets
Finally, we demonstrate that our framework may also be integrated with physics engines, to create virtual robotics environments with unique ground truth such as friction coefficients and correspondence to real scenes.
Single View Metrology in the Wild
Most 3D reconstruction methods may only recover scene properties up to a global scale ambiguity.
Bounding The Number of Linear Regions in Local Area for Neural Networks with ReLU Activations
In this paper, we present the first method to estimate the upper bound of the number of linear regions in any sphere in the input space of a given ReLU neural network.
Compression Algorithm Based on Irregular Sequence
The paper introduces a new lossless, highly robust compression algorithm that similar with LZW algorithm, yet the algorithm discards dictionary processing and uses irregular sequences with massive, random information instead.
Signal Processing 94-05 F.2.1; F.2.2
Traffic transformer: Capturing the continuity and periodicity of time series for traffic forecasting
In this work we propose a novel deep learning architecture called Traffic Transformer to capture the continuity and periodicity of time series and to model spatial dependency.
Ranked #1 on
Time Series Forecasting
on US Economy
SE-KGE: A Location-Aware Knowledge Graph Embedding Model for Geographic Question Answering and Spatial Semantic Lifting
We also construct a geographic knowledge graph as well as a set of geographic query-answer pairs called DBGeo to evaluate the performance of SE-KGE in comparison to multiple baselines.
Semantically-Enriched Search Engine for Geoportals: A Case Study with ArcGIS Online
In the geospatial aspect, we propose to enrich a query by using both place partonomy and distance decay.
Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells
The key idea is to use neural networks to convert words in texts to vector space representations based on word positions in a sentence and their contexts, which are suitable for end-to-end training of downstream tasks.
Bayesian Semi-supervised learning under nonparanormality
Semi-supervised learning is a classification method which makes use of both labeled data and unlabeled data for training.
3D Objectness Estimation via Bottom-up Regret Grouping
Further ablation study also demonstrates the effectiveness of our grouping predictor and regret mechanism.
VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results
Results of 33 object detection algorithms are presented.
TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction
Link prediction is an important and frequently studied task that contributes to an understanding of the structure of knowledge graphs (KGs) in statistical relational learning.
Contextual Graph Attention for Answering Logical Queries over Incomplete Knowledge Graphs
Recently, several studies have explored methods for using KG embedding to answer logical queries.
MMDetection: Open MMLab Detection Toolbox and Benchmark
In this paper, we introduce the various features of this toolbox.
Constrained Mutual Convex Cone Method for Image Set Based Recognition
Moreover, to enhance the framework, we introduce a discriminant space that maximizes the between-class variance (gaps) and minimizes the within-class variance of the projected convex cones onto the discriminant space, similar to the Fisher discriminant analysis.
Improved Selective Refinement Network for Face Detection
With the availability of face detection benchmark WIDER FACE dataset, much of the progresses have been made by various algorithms in recent years.
SFA: Small Faces Attention Face Detector
In this paper, we present the Small Faces Attention (SFA) face detector to better detect faces with small scale.
ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
Specifically, we first segment each car with a pre-trained Mask R-CNN, and then regress towards its 3D pose and shape based on a deformable 3D car model with or without using semantic keypoints.
ScratchDet: Training Single-Shot Object Detectors from Scratch
Taking this advantage, we are able to explore various types of networks for object detection, without suffering from the poor convergence.
A Model Parallel Proximal Stochastic Gradient Algorithm for Partially Asynchronous Systems
We prove that AsyB-ProxSGD achieves a convergence rate of $O(1/\sqrt{K})$ to stationary points for nonconvex problems under \emph{constant} minibatch sizes, where $K$ is the total number of block updates.
Android Malware Detection using Large-scale Network Representation Learning
With the growth of mobile devices and applications, the number of malicious software, or malware, is rapidly increasing in recent years, which calls for the development of advanced and effective malware detection approaches.
Cryptography and Security
Android Malware Detection based on Factorization Machine
As the popularity of Android smart phones has increased in recent years, so too has the number of malicious applications.
Cryptography and Security
Asynchronous Stochastic Proximal Methods for Nonconvex Nonsmooth Optimization
We study stochastic algorithms for solving nonconvex optimization problems with a convex yet possibly nonsmooth regularizer, which find wide applications in many practical machine learning applications.
A Block-wise, Asynchronous and Distributed ADMM Algorithm for General Form Consensus Optimization
Many machine learning models, including those with non-smooth regularizers, can be formulated as consensus optimization problems, which can be solved by the alternating direction method of multipliers (ADMM).
Learning Depth from Monocular Videos using Direct Methods
The ability to predict depth from a single image - using recent advances in CNNs - is of increasing interest to the vision community.
Semantic Photometric Bundle Adjustment on Natural Sequences
More recently, excellent results have been attained through the application of photometric bundle adjustment (PBA) methods -- which directly minimize the photometric error across frames.
Object-Centric Photometric Bundle Adjustment with Deep Shape Prior
Reconstructing 3D shapes from a sequence of images has long been a problem of interest in computer vision.
Rethinking Reprojection: Closing the Loop for Pose-Aware Shape Reconstruction From a Single Image
An emerging problem in computer vision is the reconstruction of 3D shape and pose of an object from a single image.
Rethinking Reprojection: Closing the Loop for Pose-aware ShapeReconstruction from a Single Image
An emerging problem in computer vision is the reconstruction of 3D shape and pose of an object from a single image.
Expectile Matrix Factorization for Skewed Data Analysis
Matrix factorization is a popular approach to solving matrix estimation problems based on partial observations.
The Conditional Lucas & Kanade Algorithm
In this paper, we present a new approach, referred to as the Conditional LK algorithm, which: (i) directly learns linear models that predict geometric displacement as a function of appearance, and (ii) employs a novel strategy for ensuring that the generative pixel independence assumption can still be taken advantage of.
