Search Results for author:
Found 39 papers, 15 papers with code
OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising
By enhancing trajectory prediction accuracy and addressing the challenges of out-of-sight objects, our work significantly contributes to improving the safety and reliability of autonomous driving in complex environments.
Unified Predefined-time Stability Conditions of Nonlinear Systems with Lyapunov Analysis
This brief gives a set of unified Lyapunov stability conditions to guarantee the predefined-time/finite-time stability of a dynamical systems.
Layout Sequence Prediction From Noisy Mobile Modality
In summary, our approach offers a promising solution to the challenges faced by layout sequence and trajectory prediction models in real-world settings, paving the way for utilizing sensor data from mobile phones to accurately predict pedestrian bounding box trajectories.
Camouflaged Image Synthesis Is All You Need to Boost Camouflaged Detection
This approach can serve as a plug-and-play data generation and augmentation module for existing camouflaged object detection tasks and provides a novel way to introduce more diversity and distributions into current camouflage datasets.
Imitation with Spatial-Temporal Heatmap: 2nd Place Solution for NuPlan Challenge
This paper presents our 2nd place solution for the NuPlan Challenge 2023.
Efficient Multi-Task and Transfer Reinforcement Learning with Parameter-Compositional Framework
In this work, we investigate the potential of improving multi-task training and also leveraging it for transferring in the reinforcement learning setting.
Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
With this approach, the policy previously learned offline is fully retained during online learning, thus mitigating the potential issues such as destroying the useful behaviors of the offline policy in the initial stage of online learning while allowing the offline policy participate in the exploration naturally in an adaptive manner.
Multi-Objective Evolutionary for Object Detection Mobile Architectures Search
Our improved backbone network can reduce the computational effort while improving the accuracy of the object detection network.
PaCo: Parameter-Compositional Multi-Task Reinforcement Learning
However, the gaps between contents and difficulties of different tasks bring us challenges on both which tasks should share the parameters and what parameters should be shared, as well as the optimization challenges due to parameter sharing.
Vision Transformer with Convolutions Architecture Search
The high-performance backbone network searched by VTCAS introduces the desirable features of convolutional neural networks into the Transformer architecture while maintaining the benefits of the multi-head attention mechanism.
Towards Safe Reinforcement Learning with a Safety Editor Policy
On 12 Safety Gym tasks and 2 safe racing tasks, SEditor obtains much a higher overall safety-weighted-utility (SWU) score than the baselines, and demonstrates outstanding utility performance with constraint violation rates as low as once per 2k time steps, even in obstacle-dense environments.
Do You Need the Entropy Reward (in Practice)?
On the other hand, our large-scale empirical study shows that using entropy regularization alone in policy improvement, leads to comparable or even better performance and robustness than using it in both policy improvement and policy evaluation.
Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning
GPM can therefore leverage its generated multi-step plans for temporally coordinated exploration towards high value regions, which is potentially more effective than a sequence of actions generated by perturbing each action at single step level, whose consistent movement decays exponentially with the number of exploration steps.
Fine-Grained Trajectory-based Travel Time Estimation for Multi-city Scenarios Based on Deep Meta-Learning
To tackle these challenges, we propose a meta learning based framework, MetaTTE, to continuously provide accurate travel time estimation over time by leveraging well-designed deep neural network model called DED, which consists of Data preprocessing module and Encoder-Decoder network module.
Fine-grained Identity Preserving Landmark Synthesis for Face Reenactment
Recent face reenactment works are limited by the coarse reference landmarks, leading to unsatisfactory identity preserving performance due to the distribution gap between the manipulated landmarks and those sampled from a real person.
Sketch Me A Video
Video creation has been an attractive yet challenging task for artists to explore.
TAAC: Temporally Abstract Actor-Critic for Continuous Control
TAAC has two important features: a) persistent exploration, and b) a new compare-through Q operator for multi-step TD backup, specially tailored to the action repetition scenario.
Enhanced Gradient for Differentiable Architecture Search
At the stage of block-level search, a relaxation method based on the gradient is proposed, using an enhanced gradient to design high-performance and low-complexity blocks.
Optimizing Deep Neural Networks through Neuroevolution with Stochastic Gradient Descent
Deep neural networks (DNNs) have achieved remarkable success in computer vision; however, training DNNs for satisfactory performance remains challenging and suffers from sensitivity to empirical selections of an optimization algorithm for training.
Adversarial Interpolation Training: A Simple Approach for Improving Model Robustness
We propose a simple approach for adversarial training.
Towards Adversarially Robust Object Detection
Object detection is an important vision task and has emerged as an indispensable component in many vision system, rendering its robustness as an increasingly important performance factor for practical applications.
Joint Adversarial Training: Incorporating both Spatial and Pixel Attacks
In this paper, we propose a joint adversarial training method that incorporates both spatial transformation-based and pixel-value based attacks for improving model robustness.
Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks.
Improving Sequence-to-Sequence Learning via Optimal Transport
Sequence-to-sequence models are commonly trained via maximum likelihood estimation (MLE).
Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks
To generate the adversarial image, we use one-step targeted attack with the target label being the most confusing class.
Adversarial Text Generation via Feature-Mover's Distance
However, the discrete nature of text hinders the application of GAN to text-generation tasks.
Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents
Recently there has been a rising interest in training agents, embodied in virtual environments, to perform language-directed tasks by deep reinforcement learning.
Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game
Building intelligent agents that can communicate with and learn from humans in natural language is of great value.
Interactive Grounded Language Acquisition and Generalization in a 2D World
We build a virtual agent for learning language in a 2D maze-like world.
Enhance Visual Recognition under Adverse Conditions via Deep Networks
Visual recognition under adverse conditions is a very important and challenging problem of high practical value, due to the ubiquitous existence of quality distortions during image acquisition, transmission, or storage.
Listen, Interact and Talk: Learning to Speak via Interaction
One of the long-term goals of artificial intelligence is to build an agent that can communicate intelligently with human in natural language.
A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment
We believe that our results provide some preliminary insights on how to train an agent with similar abilities in a 3D environment.
Intra-Frame Deblurring by Leveraging Inter-Frame Camera Motion
The proposed method effectively leverages the information distributed across multiple video frames due to camera motion, jointly estimating the motion between consecutive frames and blur within each frame.
Scale Adaptive Blind Deblurring
The presence of noise and small scale structures usually leads to large kernel estimation errors in blind image deblurring empirically, if not a total failure.
Multi-Shot Imaging: Joint Alignment, Deblurring and Resolution-Enhancement
Registering multiple blurry images is a challenging task due to the presence of blur while deblurring of multiple blurry images requires accurate alignment, leading to an intrinsically coupled problem.
Non-Uniform Camera Shake Removal Using a Spatially-Adaptive Sparse Penalty
Typical blur from camera shake often deviates from the standard uniform convolutional assumption, in part because of problematic rotations which create greater blurring away from some unknown center point.
Non-Uniform Blind Deblurring with a Spatially-Adaptive Sparse Prior
Typical blur from camera shake often deviates from the standard uniform convolutional script, in part because of problematic rotations which create greater blurring away from some unknown center point.
Multi-image Blind Deblurring Using a Coupled Adaptive Sparse Prior
This paper presents a robust algorithm for estimating a single latent sharp image given multiple blurry and/or noisy observations.
Revisiting Bayesian Blind Deconvolution
Blind deconvolution involves the estimation of a sharp signal or image given only a blurry observation.
