Search Results for author:
Found 43 papers, 13 papers with code
Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness
Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants.
Large-scale road network partitioning: a deep learning method based on convolutional autoencoder model
The results may suggest ways to improve the management and control of urban road network in other metropolitan cities.
Multi-source Domain Adaptation for Panoramic Semantic Segmentation
Therefore, in this paper, we propose a new task of multi-source domain adaptation for panoramic semantic segmentation, aiming to utilize both real pinhole and synthetic panoramic images in the source domains, enabling the segmentation model to perform well on unlabeled real panoramic images in the target domain.
LLMI3D: Empowering LLM with 3D Perception from a Single 2D Image
Recent advancements in autonomous driving, augmented reality, robotics, and embodied intelligence have necessitated 3D perception algorithms.
FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation
In this paper, we introduce a novel method called FRI-Net for 2D floorplan reconstruction from 3D point cloud.
MapVision: CVPR 2024 Autonomous Grand Challenge Mapless Driving Tech Report
In this competition, the organizers provided the multi-perspective camera images and standard-definition (SD) maps to explore the boundaries of scene reasoning capabilities.
More is Better: Deep Domain Adaptation with Multiple Sources
Domain adaptation (DA) aims to address this problem by aligning the distributions between the source and target domains.
LDTR: Transformer-based Lane Detection with Anchor-chain Representation
Despite recent advances in lane detection methods, scenarios with limited- or no-visual-clue of lanes due to factors such as lighting conditions and occlusion remain challenging and crucial for automated driving.
CANet: Curved Guide Line Network with Adaptive Decoder for Lane Detection
A lane instance is first responded by the heat-map on the U-shaped curved guide line at global semantic level, thus the corresponding features of each lane are aggregated at the response point.
Ranked #1 on
Lane Detection
on CurveLanes
(Recall metric)
Panacea or Placebo? Exploring Causal Effects of Nonlocal Vehicle Driving Restriction Policies on Traffic Congestion Using Difference-in-differences Approach
However, empirical evaluations of such policies have been limited.
S4OD: Semi-Supervised learning for Single-Stage Object Detection
In this paper, we design a dynamic self-adaptive threshold (DSAT) strategy in classification branch, which can automatically select pseudo labels to achieve an optimal trade-off between quality and quantity.
A Critical Analysis of Image-based Camera Pose Estimation Techniques
Camera, and associated with its objects within the field of view, localization could benefit many computer vision fields, such as autonomous driving, robot navigation, and augmented reality (AR).
2nd Place Solution for VisDA 2021 Challenge -- Universally Domain Adaptive Image Recognition
The Visual Domain Adaptation (VisDA) 2021 Challenge calls for unsupervised domain adaptation (UDA) methods that can deal with both input distribution shift and label set variance between the source and target domains.
Multi-Source Domain Adaptation for Object Detection
To reduce annotation labor associated with object detection, an increasing number of studies focus on transferring the learned knowledge from a labeled source domain to another unlabeled target domain.
Spatio-temporal Contrastive Domain Adaptation for Action Recognition
Unsupervised domain adaptation (UDA) for human action recognition is a practical and challenging problem.
2nd Place Solution for Waymo Open Dataset Challenge -- Real-time 2D Object Detection
In an autonomous driving system, it is essential to recognize vehicles, pedestrians and cyclists from images.
2nd Place Solution for Waymo Open Dataset Challenge - Real-time 2D Object Detection
In an autonomous driving system, it is essential to recognize vehicles, pedestrians and cyclists from images.
Ranked #1 on
Object Detection
on Waymo Open Dataset
A Comprehensive Survey of Scene Graphs: Generation and Application
For example, given an image, we want to not only detect and recognize objects in the image, but also know the relationship between objects (visual relationship detection), and generate a text description (image captioning) based on the image content.
Communication-efficient Byzantine-robust distributed learning with statistical guarantee
To address the two issues simultaneously, this paper develops two communication-efficient and robust distributed learning algorithms for convex problems.
SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training
Results show that: 1) applied to inference, SD achieves up to 2. 44x energy efficiency as evaluated via real hardware implementations; 2) applied to training, SD leads to 10. 56x and 4. 48x reduction in the storage and training energy, with negligible accuracy loss compared to state-of-the-art training baselines.
Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptation
First, we generate an adapted domain to align the source and target domains on the pixel-level by improving CycleGAN with a multi-scale structured cycle-consistency loss.
Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources
C-CycleGAN transfers source samples at instance-level to an intermediate domain that is closer to the target domain with sentiment semantics preserved and without losing discriminative features.
ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation
They require prior knowledge of real-world statistics and ignore the pixel-level dropout noise gap and the spatial feature gap between different domains.
Emotion-Based End-to-End Matching Between Image and Music in Valence-Arousal Space
In this paper, we study end-to-end matching between image and music based on emotions in the continuous valence-arousal (VA) space.
Rethinking Distributional Matching Based Domain Adaptation
In this paper, in order to devise robust DA algorithms, we first systematically analyze the limitations of DM based methods, and then build new benchmarks with more realistic domain shifts to evaluate the well-accepted DM methods.
TIMELY: Pushing Data Movements and Interfaces in PIM Accelerators Towards Local and in Time Domain
Resistive-random-access-memory (ReRAM) based processing-in-memory (R$^2$PIM) accelerators show promise in bridging the gap between Internet of Thing devices' constrained resources and Convolutional/Deep Neural Networks' (CNNs/DNNs') prohibitive energy cost.
Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks
Finally, we leverage the existence of EB tickets and the proposed mask distance to develop efficient training methods, which are achieved by first identifying EB tickets via low-cost schemes, and then continuing to train merely the EB tickets towards the target accuracy.
Frontoparietal Connectivity Neurofeedback Training for Promotion of Working Memory: An fNIRS Study in Healthy Male Participants
Neurofeedback cognitive training is a promising tool used to promote cognitive functions effectively and efficiently.
Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
Therefore, transferring the learned knowledge from a separate, labeled source domain to an unlabeled or sparsely labeled target domain becomes an appealing alternative.
DNN-Chip Predictor: An Analytical Performance Predictor for DNN Accelerators with Various Dataflows and Hardware Architectures
The recent breakthroughs in deep neural networks (DNNs) have spurred a tremendously increased demand for DNN accelerators.
MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
Finally, feature-level alignment is performed between the aggregated domain and the target domain while training the task network.
An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos
Emotion recognition in user-generated videos plays an important role in human-centered computing.
Ranked #4 on
Video Emotion Recognition
on Ekman6
AutoDNNchip: An Automated DNN Chip Predictor and Builder for Both FPGAs and ASICs
Specifically, AutoDNNchip consists of two integrated enablers: (1) a Chip Predictor, built on top of a graph-based accelerator representation, which can accurately and efficiently predict a DNN accelerator's energy, throughput, and area based on the DNN model parameters, hardware configuration, technology-based IPs, and platform constraints; and (2) a Chip Builder, which can automatically explore the design space of DNN chips (including IP selection, block configuration, resource balancing, etc.
Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference
The core idea of DFS is to hypothesize layer-wise quantization (to different bitwidths) as intermediate "soft" choices to be made between fully utilizing and skipping a layer.
Multi-source Distilling Domain Adaptation
Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA).
Domain Adaptation
Multi-Source Unsupervised Domain Adaptation
E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings
Extensive simulations and ablation studies, with real energy measurements from an FPGA board, confirm the superiority of our proposed strategies and demonstrate remarkable energy savings for training.
Multi-source Domain Adaptation for Semantic Segmentation
In this paper, we propose to investigate multi-source domain adaptation for semantic segmentation.
Ranked #2 on
Domain Adaptation
on GTA5+Synscapes to Cityscapes
Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks
In this paper, we discover for the first time that the winning tickets can be identified at the very early training stage, which we term as early-bird (EB) tickets, via low-cost training schemes (e. g., early stopping and low-precision training) at large learning rates.
ROAM: Recurrently Optimizing Tracking Model
In this paper, we design a tracking model consisting of response generation and bounding box regression, where the first component produces a heat map to indicate the presence of the object at different positions and the second part regresses the relative bounding box shifts to anchors mounted on sliding-window locations.
Dual Dynamic Inference: Enabling More Efficient, Adaptive and Controllable Deep Inference
State-of-the-art convolutional neural networks (CNNs) yield record-breaking predictive performance, yet at the cost of high-energy-consumption inference, that prohibits their widely deployments in resource-constrained Internet of Things (IoT) applications.
Performance Evaluation of Deep Learning Tools in Docker Containers
We first benchmark the performance of system components (IO, CPU and GPU) in a docker container and the host system and compare the results to see if there's any difference.
Supervised Learning Based Algorithm Selection for Deep Neural Networks
In this paper, we target at optimizing the operations of multiplying a matrix with the transpose of another matrix (referred to as NT operation hereafter), which contribute about half of the training time of fully connected deep neural networks.
Benchmarking State-of-the-Art Deep Learning Software Tools
We first benchmark the running performance of these tools with three popular types of neural networks on two CPU platforms and three GPU platforms.
