Search Results for author:
Found 19 papers, 6 papers with code
Sample-efficient Unsupervised Policy Cloning from Ensemble Self-supervised Labeled Videos
In this paper, we try to let machines replicate this efficient watching-and-learning process through Unsupervised Policy from Ensemble Self-supervised labeled Videos (UPESV), a novel framework to efficiently learn policies from videos without any other expert supervision.
GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation
To address these challenges, we introduced a large-scale part-centric dataset for articulated object manipulation that features both photo-realistic material randomization and detailed annotations of part-oriented, scene-level actionable interaction poses.
Learning Future Representation with Synthetic Observations for Sample-efficient Reinforcement Learning
Employing auxiliary tasks allows the agent to enhance visual representation in a targeted manner, thereby improving the sample efficiency and performance of downstream RL.
RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction tasks
To address the problem, we propose a RoboGPT agent\footnote{our code and dataset will be released soon} for making embodied long-term decisions for daily tasks, with two modules: 1) LLMs-based planning with re-plan to break the task into multiple sub-goals; 2) RoboSkill individually designed for sub-goals to learn better navigation and manipulation skills.
ComSD: Balancing Behavioral Quality and Diversity in Unsupervised Skill Discovery
It contains a particle-based exploration reward to make agents access far-reaching states for exploratory skill acquisition, and a novel contrastive diversity reward to promote the discriminability between different skills.
Multi-modal Learning based Prediction for Disease
From the dataset, we quantitatively analyze and select clinical metadata that most contribute to NAFLD prediction.
Cross-domain Random Pre-training with Prototypes for Reinforcement Learning
CRPTpro significantly outperforms the next best Proto-RL(C) on 11/12 cross-domain downstream tasks with only 54\% wall-clock pre-training time, exhibiting state-of-the-art pre-training performance with greatly improved pre-training efficiency.
BViT: Broad Attention based Vision Transformer
In this paper, we propose the broad attention to improve the performance by incorporating the attention relationship of different layers for vision transformer, which is called BViT.
Stacked BNAS: Rethinking Broad Convolutional Neural Network for Neural Architecture Search
Moreover, multi-scale feature fusion and knowledge embedding are proposed to improve the performance of BCNN with shallow topology.
ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Search
Compared with the traditional rule-based pruning method, this pipeline saves human labor and achieves a higher compression ratio with lower accuracy loss.
Heuristic Rank Selection with Progressively Searching Tensor Ring Network
Interestingly, we discover that part of the rank elements is sensitive and usually aggregate in a narrow region, namely an interest region.
BNAS-v2: Memory-efficient and Performance-collapse-prevented Broad Neural Architecture Search
For this consequent issue, two solutions are given: 1) we propose Confident Learning Rate (CLR) that considers the confidence of gradient for architecture weights update, increasing with the training time of over-parameterized BCNN; 2) we introduce the combination of partial channel connections and edge normalization that also can improve the memory efficiency further.
ContourRend: A Segmentation Method for Improving Contours by Rendering
A good object segmentation should contain clear contours and complete regions.
BiFNet: Bidirectional Fusion Network for Road Segmentation
Considering the bird's eye views(BEV) of the LiDAR remains the space structure in horizontal plane, this paper proposes a bidirectional fusion network(BiFNet) to fuse the image and BEV of the point cloud.
ModuleNet: Knowledge-inherited Neural Architecture Search
Unlike previous search algorithms, and benefiting from inherited knowledge, our method is able to directly search for architectures in the macro space by NSGA-II algorithm without tuning parameters in these \textit{module}s. Experiments show that our strategy can efficiently evaluate the performance of new architecture even without tuning weights in convolutional layers.
BNAS:An Efficient Neural Architecture Search Approach Using Broad Scalable Architecture
In this paper, we propose Broad Neural Architecture Search (BNAS) where we elaborately design broad scalable architecture dubbed Broad Convolutional Neural Network (BCNN) to solve the above issue.
Graph-FCN for image semantic segmentation
Then we apply graph convolutional network to solve this graph node classification problem.
Lane Change Decision-making through Deep Reinforcement Learning with Rule-based Constraints
Autonomous driving decision-making is a great challenge due to the complexity and uncertainty of the traffic environment.
Reinforcement Learning and Deep Learning based Lateral Control for Autonomous Driving
The control module which is based on reinforcement learning then makes a control decision based on these features.
