Search Results for author:
Found 75 papers, 32 papers with code
Exploring Inter-Channel Correlation for Diversity-Preserved Knowledge Distillation
Extensive experiments on two vision tasks, including ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consistently outperforms many existing methods, advancing the state-of-the-art in the fields of Knowledge Distillation.
Ranked #21 on
Knowledge Distillation
on ImageNet
BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework
Fusing the camera and LiDAR information has become a de-facto standard for 3D object detection tasks.
A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence
Deep learning based localization and mapping has recently attracted significant attention.
RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision
3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels.
Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation
The robustness of Text-to-SQL parsers against adversarial perturbations plays a crucial role in delivering highly reliable applications.
RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds
We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds.
DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images
In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views.
Dynamic Slimmable Network
Here, we explore a dynamic network slimming regime, named Dynamic Slimmable Network (DS-Net), which aims to achieve good hardware-efficiency via dynamically adjusting filter numbers of networks at test time with respect to different inputs, while keeping filters stored statically and contiguously in hardware to prevent the extra burden.
DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers
Dynamic networks have shown their promising capability in reducing theoretical computation complexity by adapting their architectures to the input during inference.
FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
Matching cross-modality features between images and point clouds is a fundamental problem for image-to-point cloud registration.
GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds
Our method consists of three major components, 1) the feature extractor to learn per-point features from input point clouds, 2) the superpoint constructor to progressively grow the sizes of superpoints, and 3) the semantic primitive clustering module to group superpoints into semantic elements for the final semantic segmentation.
BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search
In this work, we present Block-wisely Self-supervised Neural Architecture Search (BossNAS), an unsupervised NAS method that addresses the problem of inaccurate architecture rating caused by large weight-sharing space and biased supervision in previous methods.
AtLoc: Attention Guided Camera Localization
Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers.
Ranked #2 on
Visual Localization
on Oxford RobotCar Full
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
Our framework comprises a core decomposer agent for Text-to-SQL generation with few-shot chain-of-thought reasoning, accompanied by two auxiliary agents that utilize external tools or models to acquire smaller sub-databases and refine erroneous SQL queries.
Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection
There are two critical sensors for 3D perception in autonomous driving, the camera and the LiDAR.
See Through Smoke: Robust Indoor Mapping with Low-cost mmWave Radar
This paper presents the design, implementation and evaluation of milliMap, a single-chip millimetre wave (mmWave) radar based indoor mapping system targetted towards low-visibility environments to assist in emergency response.
P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching
Accurately describing and detecting 2D and 3D keypoints is crucial to establishing correspondences across images and point clouds.
Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networks
Simultaneous Localization and Mapping (SLAM) system typically employ vision-based sensors to observe the surrounding environment.
Enhancing Large Language Model with Self-Controlled Memory Framework
Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.
DAA: A Delta Age AdaIN operation for age estimation via binary code transformer
Inspired by the transfer learning, we designed the Delta Age AdaIN (DAA) operation to obtain the feature difference with each age, which obtains the style map of each age through the learned values representing the mean and standard deviation.
A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task, which focuses on detecting the sentiment polarity towards the aspect in a sentence.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+4
No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces
Scene flow is a powerful tool for capturing the motion field of 3D point clouds.
Ranked #1 on
3D Action Recognition
on NTU RGB+D
Knowledge Distillation via the Target-aware Transformer
To this end, we propose a novel one-to-all spatial matching knowledge distillation approach.
CubeLearn: End-to-end Learning for Human Motion Recognition from Raw mmWave Radar Signals
To avoid the drawbacks of conventional DFT pre-processing, we propose a learnable pre-processing module, named CubeLearn, to directly extract features from raw radar signal and build an end-to-end deep neural network for mmWave FMCW radar motion recognition applications.
Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillation
Extensive experiments on two vision tasks, includ-ing ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consis-tently outperforms many existing methods, advancing thestate-of-the-art in the fields of Knowledge Distillation.
PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization
In this paper, we present a novel end-to-end learning-based LiDAR relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input, without requiring a pre-built map.
Robotics
Know What I don't Know: Handling Ambiguous and Unanswerable Questions for Text-to-SQL
Following this study, we propose a simple yet effective counterfactual example generation approach that automatically produces ambiguous and unanswerable text-to-SQL examples.
Sparse Attentive Memory Network for Click-through Rate Prediction with Long Sequences
SAM supports efficient training and real-time inference for user behavior sequences with lengths on the scale of thousands.
Unsupervised Sentence Representation Learning with Frequency-induced Adversarial Tuning and Incomplete Sentence Filtering
To solve the problems, we fine-tune PLMs by leveraging the frequency information of words and propose a novel USRL framework, namely Sentence Representation Learning with Frequency-induced Adversarial tuning and Incomplete sentence filtering (SLT-FAI).
Contrastive Instruction-Trajectory Learning for Vision-Language Navigation
The vision-language navigation (VLN) task requires an agent to reach a target with the guidance of natural language instruction.
VMLoc: Variational Fusion For Learning-Based Multimodal Camera Localization
We conjecture that this is because of the naive approaches to feature space fusion through summation or concatenation which do not take into account the different strengths of each modality.
Learning Hierarchical Features for Visual Object Tracking with Recursive Neural Networks
First, we learn RNN parameters to discriminate between the target object and background in the first frame of a test sequence.
Joint Calibration of Panoramic Camera and Lidar Based on Supervised Learning
In view of contemporary panoramic camera-laser scanner system, the traditional calibration method is not suitable for panoramic cameras whose imaging model is extremely nonlinear.
Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association
Then the Siamese CNN and temporally constrained metrics are jointly learned online to construct the appearance-based tracklet affinity models.
Tracklet Association by Online Target-Specific Metric Learning and Coherent Dynamics Estimation
In this paper, we present a novel method based on online target-specific metric learning and coherent dynamics estimation for tracklet (track fragment) association by network flow optimization in long-term multi-person tracking.
Scene Parsing with Integration of Parametric and Non-parametric Models
The local beliefs of pixels are output by CNN-Ensemble.
Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks
In this manuscript, we integrate CNNs with HRNNs, and develop end-to-end convolutional hierarchical recurrent neural networks (C-HRNNs).
DAG-Recurrent Neural Networks For Scene Labeling
In image labeling, local representations for image units are usually generated from their surrounding image patches, thus long-range contextual information is not effectively encoded.
Ranked #18 on
Semantic Segmentation
on COCO-Stuff test
Radial basis function process neural network training based on generalized frechet distance and GA-SA hybrid strategy
For learning problem of Radial Basis Function Process Neural Network (RBF-PNN), an optimization training method based on GA combined with SA is proposed in this paper.
Tracklet Association with Online Target-Specific Metric Learning
In our method, target-specific similarity metrics are learned, which give rise to the appearance-based models used in the tracklet affinity estimation.
Integrating Parametric and Non-Parametric Models For Scene Labeling
We adopt Convolutional Neural Networks (CNN) as our parametric model to learn discriminative features and classifiers for local patch classification.
Accelerating Primal Solution Findings for Mixed Integer Programs Based on Solution Prediction
In many applications, a similar MIP model is solved on a regular basis, maintaining remarkable similarities in model structures and solution appearances but differing in formulation coefficients.
X-LineNet: Detecting Aircraft in Remote Sensing Images by a pair of Intersecting Line Segments
Motivated by the development of deep convolution neural networks (DCNNs), tremendous progress has been gained in the field of aircraft detection.
DynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction
In addition we show how DynaNet can indicate failures through investigation of properties such as the rate of innovation (Kalman Gain).
Chinese Spelling Error Detection Using a Fusion Lattice LSTM
Spelling error detection serves as a crucial preprocessing in many natural language processing applications.
ATCSpeech: a multilingual pilot-controller speech corpus from real Air Traffic Control environment
To our best knowledge, this is the first work that aims at building a real and multilingual ASR corpus for the air traffic related research.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Learning Selective Sensor Fusion for States Estimation
By integrating the observations from different sensors, these mobile agents are able to perceive the environment and estimate system states, e. g. locations and orientations.
PSF-LO: Parameterized Semantic Features Based Lidar Odometry
Lidar odometry (LO) is a key technology in numerous reliable and accurate localization and mapping systems of autonomous driving.
Photonic Floquet time crystals
The public and scientists constantly have different perspectives.
Quantum Physics Mesoscale and Nanoscale Physics Other Condensed Matter Optics
Relational Deep Reinforcement Learning for Routing in Wireless Networks
While routing in wireless networks has been studied extensively, existing protocols are typically designed for a specific set of network conditions and so cannot accommodate any drastic changes in those conditions.
An AI-assisted Economic Model of Endogenous Mobility and Infectious Diseases: The Case of COVID-19 in the United States
We build a deep-learning-based SEIR-AIM model integrating the classical Susceptible-Exposed-Infectious-Removed epidemiology model with forecast modules of infection, community mobility, and unemployment.
A novel class of fixed-time consensus protocols for multi-agent systems with simple dynamics
This paper investigates the fixed-time consensus problem for a class of multi-agent systems with simple dynamics.
Iterative Memory Network for Long Sequential User Behavior Modeling in Recommender Systems
Extensive empirical studies show that our method outperforms various state-of-the-art sequential modeling methods on both public and industrial datasets for long sequential user behavior modeling.
Weakly Supervised Prototype Topic Model with Discriminative Seed Words: Modifying the Category Prior by Self-exploring Supervised Signals
The recent generative dataless methods construct document-specific category priors by using seed word occurrences only, however, such category priors often contain very limited and even noisy supervised signals.
Learning an Adaptive Forwarding Strategy for Mobile Wireless Networks: Resource Usage vs. Latency
Designing effective routing strategies for mobile wireless networks is challenging due to the need to seamlessly adapt routing behavior to spatially diverse and temporally changing network conditions.
DMML-Net: Deep Metametric Learning for Few-Shot Geographic Object Segmentation in Remote Sensing Imagery
After metatraining, DMML-Net can be applied for the few-shot segmentation tasks of novel geographic objects with only a few gradient steps on the small training set.
Decoupling Skill Learning from Robotic Control for Generalizable Object Manipulation
Our experiments on manipulating complex articulated objects show that the proposed approach is more generalizable to unseen objects with large intra-class variations, outperforming previous approaches.
Non-stationary Projection-free Online Learning with Dynamic and Adaptive Regret Guarantees
Specifically, we first provide a novel dynamic regret analysis for an existing projection-free method named $\text{BOGD}_\text{IP}$, and establish an $\mathcal{O}(T^{3/4}(1+P_T))$ dynamic regret bound, where $P_T$ denotes the path-length of the comparator sequence.
MPSTAN: Metapopulation-based Spatio-Temporal Attention Network for Epidemic Forecasting
Most of the present spatio-temporal models cannot provide a general framework for stable, and accurate forecasting of epidemics with diverse evolution trends.
Deep Learning for Visual Localization and Mapping: A Survey
Deep learning based localization and mapping approaches have recently emerged as a new research direction and receive significant attentions from both industry and academia.
Simultaneous Localization and Mapping
Visual Localization
+1
Drone-NeRF: Efficient NeRF Based 3D Scene Reconstruction for Large-Scale Drone Survey
In this work, we propose the Drone-NeRF framework to enhance the efficient reconstruction of unbounded large-scale scenes suited for drone oblique photography using Neural Radiance Fields (NeRF).
Improving Opioid Use Disorder Risk Modelling through Behavioral and Genetic Feature Integration
Opioids are an effective analgesic for acute and chronic pain, but also carry a considerable risk of addiction leading to millions of opioid use disorder (OUD) cases and tens of thousands of premature deaths in the United States yearly.
Early detection of inflammatory arthritis to improve referrals using multimodal machine learning from blood testing, semi-structured and unstructured patient records
But in practice, blood testing data is not always available at the point of referrals, so we need methods to leverage multimodal data such as semi-structured and unstructured data for early detection of IA.
Backbone-based Dynamic Graph Spatio-Temporal Network for Epidemic Forecasting
To capture this property, we use adaptive methods to generate static backbone graphs containing the primary information and temporal models to generate dynamic temporal graphs of epidemic data, fusing them to generate a backbone-based dynamic graph.
FAGC:Feature Augmentation on Geodesic Curve in the Pre-Shape Space
Finally, the many generated features on the Geodesic curve are used to train the various machine learning models.
Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations
And we propose an ABSA-specific augmentation method to create such augmentations.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Few-shot Image Generation via Information Transfer from the Built Geodesic Surface
Images generated by most of generative models trained with limited data often exhibit deficiencies in either fidelity, diversity, or both.
xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning
To bridge the gap among different languages, we propose a cross-lingual instruction fine-tuning framework (xCOT) to transfer knowledge from high-resource languages to low-resource languages.
NeuV-SLAM: Fast Neural Multiresolution Voxel Optimization for RGBD Dense SLAM
We introduce NeuV-SLAM, a novel dense simultaneous localization and mapping pipeline based on neural multiresolution voxels, characterized by ultra-fast convergence and incremental expansion capabilities.
HCPM: Hierarchical Candidates Pruning for Efficient Detector-Free Matching
Deep learning-based image matching methods play a crucial role in computer vision, yet they often suffer from substantial computational demands.
SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field
Vision-centric 3D environment understanding is both vital and challenging for autonomous driving systems.
Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians
In this study, we explore the challenge of efficiently representing scenes with a constrained number of Gaussians.
Self-Supervised Multi-Frame Neural Scene Flow
Neural Scene Flow Prior (NSFP) and Fast Neural Scene Flow (FNSF) have shown remarkable adaptability in the context of large out-of-distribution autonomous driving.
m3P: Towards Multimodal Multilingual Translation with Multimodal Prompt
Our method aims to minimize the representation distance of different languages by regarding the image as a central language.
Deep image learning of quantitative structure-property relationships of cooper alloys via feature augmentation on Geodesic curve in shape space
These outcomes underscore the potential of FAGC to address the challenge of limited image data in materials science, providing a powerful tool for establishing detailed and quantitative relationships between complex microstructures and material properties.
