Search Results for author:
Found 69 papers, 42 papers with code
JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data
However, the over-reliance on real labeled data in LiDAR perception limits the scale of on-road attempts.
3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer
Current 3D Large Multimodal Models (3D LMMs) have shown tremendous potential in 3D-vision-based dialogue and reasoning.
Are Expressive Models Truly Necessary for Offline RL?
Among various branches of offline reinforcement learning (RL) methods, goal-conditioned supervised learning (GCSL) has gained increasing popularity as it formulates the offline RL problem as a sequential modeling task, therefore bypassing the notoriously difficult credit assignment challenge of value learning in conventional RL paradigm.
MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment
Specifically, we first propose Mask-Text Decoder that enhances the mask representations using rich textual data with the CLIP language model.
A Generalized Version of Chung's Lemma and its Applications
Chung's lemma is a classical tool for establishing asymptotic convergence rates of (stochastic) optimization methods under strong convexity-type assumptions and appropriate polynomial diminishing step sizes.
Image Copy-Move Forgery Detection and Localization Scheme: How to Avoid Missed Detection and False Alarm
Image copy-move is an operation that replaces one part of the image with another part of the same image, which can be used for illegal purposes due to the potential semantic changes.
Hummer: Towards Limited Competitive Preference Dataset
Preference datasets are essential for incorporating human preferences into pre-trained language models, playing a key role in the success of Reinforcement Learning from Human Feedback.
Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities
Then, we introduce LLM-enabled key techniques and telecom applications in terms of generation, classification, optimization, and prediction problems.
Unified Language-driven Zero-shot Domain Adaptation
This paper introduces Unified Language-driven Zero-shot Domain Adaptation (ULDA), a novel task setting that enables a single model to adapt to diverse target domains without explicit domain-ID knowledge.
OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
This exploration led to the creation of Omni-Adaptive 3D CNNs (OA-CNNs), a family of networks that integrates a lightweight module to greatly enhance the adaptivity of sparse CNNs at minimal computational cost.
Ranked #5 on
3D Semantic Segmentation
on SemanticKITTI
(val mIoU metric)
AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving
As an essential task in autonomous driving (AD), motion prediction aims to predict the future states of surround objects for navigation.
GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding
To address this issue, we propose GroupContrast, a novel approach that combines segment grouping and semantic-aware contrastive learning.
GiT: Towards Generalist Vision Transformer through Universal Language Interface
Due to its simple design, this paradigm holds promise for narrowing the architectural gap between vision and language.
Ranked #2 on
Video Captioning
on MSVD-CTN
(using extra training data)
TBI Image/Text (TBI-IT): Comprehensive Text and Image Datasets for Traumatic Brain Injury Research
In this paper, we introduce a new dataset in the medical field of Traumatic Brain Injury (TBI), called TBI-IT, which includes both electronic medical records (EMRs) and head CT images.
HICH Image/Text (HICH-IT): Comprehensive Text and Image Datasets for Hypertensive Intracerebral Hemorrhage Research
Index Terms-HICH, Deep learning, Intraparenchymal hemorrhage, named entity recognition, novel dataset
Point Transformer V3: Simpler Faster Stronger
This paper is not motivated to seek innovation within the attention mechanism.
Open-Vocabulary 3D Semantic Segmentation with Foundation Models
In dynamic 3D environments the ability to recognize a diverse range of objects without the constraints of predefined categories is indispensable for real-world applications.
3D Semantic Segmentation
Open Vocabulary Semantic Segmentation
+2
Training Vision Transformers for Semi-Supervised Semantic Segmentation
We present S4Former a novel approach to training Vision Transformers for Semi-Supervised Semantic Segmentation (S4).
An Effective Image Copy-Move Forgery Detection Using Entropy Information
Therefore, this paper introduces entropy images to determine the coordinates and scales of keypoints based on Scale Invariant Feature Transform detector, which make the pre-processing more suitable for solving the above problems.
Point Transformer V3: Simpler, Faster, Stronger
This paper is not motivated to seek innovation within the attention mechanism.
Ranked #1 on
3D Semantic Segmentation
on ScanNet++
(using extra training data)
LiON: Learning Point-wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data
We demonstrate that learning different abstaining penalties, apart from point-wise penalty, for different types of (synthesized) outliers can further improve the performance.
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks.
Offline Reinforcement Learning with Imbalanced Datasets
The prevalent use of benchmarks in current offline reinforcement learning (RL) research has led to a neglect of the imbalance of real-world dataset distributions in the development of models.
MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Querying
Extensive experimental results demonstrate that the MTR framework achieves state-of-the-art performance on the highly-competitive motion prediction benchmarks, while the MTR++ framework surpasses its precursor, exhibiting enhanced performance and efficiency in predicting accurate multimodal future trajectories for multiple agents.
Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL
Based on extensive experiments, we find TSRL achieves great performance on small benchmark datasets with as few as 1% of the original samples, which significantly outperforms the recent offline RL algorithms in terms of data efficiency and generalizability. Code is available at: https://github. com/pcheng2/TSRL
FreePoint: Unsupervised Point Cloud Instance Segmentation
Based on the point features, we perform a bottom-up multicut algorithm to segment point clouds into coarse instance masks as pseudo labels, which are used to train a point cloud instance segmentation model.
Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understanding
Masked signal modeling has greatly advanced self-supervised pre-training for language and 2D images.
A Deep Learning Framework for Traffic Data Imputation Considering Spatiotemporal Dependencies
Spatiotemporal (ST) data collected by sensors can be represented as multi-variate time series, which is a sequence of data points listed in an order of time.
Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization
This gives a deeper understanding of why the in-sample learning paradigm works, i. e., it applies implicit value regularization to the policy.
Learning Context-aware Classifier for Semantic Segmentation
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing.
A Policy-Guided Imitation Approach for Offline Reinforcement Learning
We decompose the conventional reward-maximizing policy in offline RL into a guide-policy and an execute-policy.
Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
In this work, we analyze the limitations of the Point Transformer and propose our powerful and efficient Point Transformer V2 model with novel designs that overcome the limitations of previous work.
Ranked #1 on
3D Semantic Segmentation
on nuScenes
Motion Transformer with Global Intention Localization and Local Movement Refinement
Predicting multimodal future behavior of traffic participants is essential for robotic vehicles to make safe decisions.
MTR-A: 1st Place Solution for 2022 Waymo Open Dataset Challenge -- Motion Prediction
In this report, we present the 1st place solution for motion prediction track in 2022 Waymo Open Dataset Challenges.
SuperVessel: Segmenting High-resolution Vessel from Low-resolution Retinal Image
Vascular segmentation extracts blood vessels from images and serves as the basis for diagnosing various diseases, like ophthalmic diseases.
Boosting Single-Frame 3D Object Detection by Simulating Multi-Frame Point Clouds
To boost a detector for single-frame 3D object detection, we present a new approach to train it to simulate features and responses following a detector trained on multi-frame point clouds.
Boosting 3D Object Detection by Simulating Multimodality on Point Clouds
This paper presents a new approach to boost a single-modality (LiDAR) 3D object detector by teaching it to simulate features and responses that follow a multi-modality (LiDAR-image) detector.
Global Mixup: Eliminating Ambiguity with Clustering
(2) linear combination significantly limits the sampling space for generating samples.
DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation
Deep learning approaches achieve prominent success in 3D semantic segmentation.
Stratified Transformer for 3D Point Cloud Segmentation
In this paper, we propose Stratified Transformer that is able to capture long-range contexts and demonstrates strong generalization ability and high performance.
Ranked #19 on
Semantic Segmentation
on ScanNet
DNN Training Acceleration via Exploring GPGPU Friendly Sparsity
The training phases of Deep neural network~(DNN) consumes enormous processing time and energy.
CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction
We explore the sparsity in ViT and observe that informative patches and heads are sufficient for accurate image recognition.
A Unified Query-based Paradigm for Point Cloud Understanding
This is achieved by introducing an intermediate representation, i. e., Q-representation, in the querying stage to serve as a bridge between the embedding stage and task heads.
Ranked #7 on
Semantic Segmentation
on S3DIS
Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals
This paper presents a new PIM architecture to efficiently accelerate deep learning tasks by minimizing the required A/D conversions with analog accumulation and neural approximated peripheral circuits.
N3H-Core: Neuron-designed Neural Network Accelerator via FPGA-based Heterogeneous Computing Cores
From the software perspective, we mathematically and systematically model the latency and resource utilization of the proposed heterogeneous accelerator, regarding varying system design configurations.
Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation
To address the high cost and challenges of 3D point-level labeling, we present a method for semi-supervised point cloud semantic segmentation to adopt unlabeled point clouds in training to boost the model performance.
Semi-supervised Semantic Segmentation with Directional Context-aware Consistency
Semantic segmentation has made tremendous progress in recent years.
AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference
This paper presents AppealNet, a novel edge/cloud collaborative architecture that runs deep learning (DL) tasks more efficiently than state-of-the-art solutions.
Skimming and Scanning for Untrimmed Video Action Recognition
Video action recognition (VAR) is a primary task of video understanding, and untrimmed videos are more common in real-life scenes.
SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud
Lastly, to better exploit hard targets, we design an ODIoU loss to supervise the student with constraints on the predicted box centers and orientations.
Ranked #1 on
Birds Eye View Object Detection
on KITTI Cars Easy
Bidirectional Projection Network for Cross Dimension Scene Understanding
Via the \emph{BPM}, complementary 2D and 3D information can interact with each other in multiple architectural levels, such that advantages in these two visual domains can be combined for better scene recognition.
Ranked #21 on
Semantic Segmentation
on ScanNet
Detecting anomalous quartic gauge couplings using the isolation forest machine learning algorithm
The search of new physics~(NP) beyond the Standard Model is one of the most important tasks of high energy physics.
High Energy Physics - Phenomenology
SME: ReRAM-based Sparse-Multiplication-Engine to Squeeze-Out Bit Sparsity of Neural Network
However, it is challenging for crossbar architecture to exploit the sparsity in the DNN.
PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection
3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields.
Ranked #2 on
3D Object Detection
on KITTI Cars Easy val
Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-Point
Model quantization has emerged as a mandatory technique for efficient inference with advanced Deep Neural Networks (DNN).
Point Transformer
For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70. 4% on Area 5, outperforming the strongest prior model by 3. 3 absolute percentage points and crossing the 70% mIoU threshold for the first time.
Ranked #4 on
3D Semantic Segmentation
on S3DIS
CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud
Existing single-stage detectors for locating objects in point clouds often treat object localization and category classification as separate tasks, so the localization accuracy and classification confidence may not well align.
Ranked #3 on
Birds Eye View Object Detection
on KITTI Cars Easy
Generalized Few-shot Semantic Segmentation
Then, since context is essential for semantic segmentation, we propose the Context-Aware Prototype Learning (CAPL) that significantly improves performance by 1) leveraging the co-occurrence prior knowledge from support samples, and 2) dynamically enriching contextual information to the classifier, conditioned on the content of each query image.
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
Instance segmentation is an important task for scene understanding.
Ranked #9 on
3D Instance Segmentation
on STPLS3D
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds.
Advances in Online Audio-Visual Meeting Transcription
This increases marginally to 1. 6% when 50% of the attendees are unknown to the system.
Measurement Scheduling for Cooperative Localization in Resource-Constrained Conditions
Optimal selection of which teammates a robot should take a relative measurement from such that the updated joint localization uncertainty of the team is minimized is an NP-hard problem.
Robotics
Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation
To incorporate point features in the edge branch, we establish a hierarchical graph framework, where the graph is initialized from a coarse layer and gradually enriched along the point decoding process.
Ranked #46 on
Semantic Segmentation
on S3DIS Area5
An Ultra-Efficient Memristor-Based DNN Framework with Structured Weight Pruning and Quantization Using ADMM
Memristor-based weight pruning and weight quantization have been seperately investigated and proven effectiveness in reducing area and power consumption compared to the original DNN model.
Efficient GAN-based method for cyber-intrusion detection
Ubiquitous anomalies endanger the security of our system constantly.
Invocation-driven Neural Approximate Computing with a Multiclass-Classifier and Multiple Approximators
We thus propose a novel approximate computing architecture with a Multiclass-Classifier and Multiple Approximators (MCMA).
GAL: Geometric Adversarial Loss for Single-View 3D-Object Reconstruction
We propose to add geometric adversarial loss (GAL).
AXNet: ApproXimate computing using an end-to-end trainable neural network
To guarantee the approximation quality, existing works deploy two neural networks (NNs), e. g., an approximator and a predictor.
Approximate Random Dropout
In this paper, we propose the Approximate Random Dropout that replaces the conventional random dropout of neurons and synapses with a regular and predefined patterns to eliminate the unnecessary computation and data access.
