Search Results for author:
Found 35 papers, 16 papers with code
A Deep Policy Inference Q-Network for Multi-Agent Systems
DPIQN incorporates the learned policy features as a hidden vector into its own deep Q-network (DQN), such that it is able to predict better Q values for the controllable agents than the state-of-the-art deep reinforcement learning models.
Virtual-to-Real: Learning to Control in Visual Semantic Segmentation
Collecting training data from the physical world is usually time-consuming and even dangerous for fragile robots, and thus, recent advances in robot learning advocate the use of simulators as the training platform.
Diversity-Driven Exploration Strategy for Deep Reinforcement Learning
Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards.
Dynamic Video Segmentation Network
We explore the use of a decision network to adaptively assign different frame regions to different networks based on a metric called expected confidence score.
Adversarial Active Exploration for Inverse Dynamics Model Learning
Our framework consists of a deep reinforcement learning (DRL) agent and an inverse dynamics model contesting with each other.
Visual Relationship Prediction via Label Clustering and Incorporation of Depth Information
The additional depth prediction path supplements the relationship prediction model in a way that bounding boxes or segmentation masks are unable to deliver.
Never Forget: Balancing Exploration and Exploitation via Learning Optical Flow
We propose to employ optical flow estimation errors to examine the novelty of new observations, such that agents are able to memorize and understand the visited states in a more comprehensive fashion.
Adversarial Exploration Strategy for Self-Supervised Imitation Learning
Our framework consists of a deep reinforcement learning (DRL) agent and an inverse dynamics model contesting with each other.
A Self-Supervised Method for Mapping Human Instructions to Robot Policies
In this paper, we propose a modular approach which separates the instruction-to-action mapping procedure into two separate stages.
Exploration via Flow-Based Intrinsic Rewards
Exploration bonuses derived from the novelty of observations in an environment have become a popular approach to motivate exploration for reinforcement learning (RL) agents in the past few years.
Reusability and Transferability of Macro Actions for Reinforcement Learning
However, by using a proper macro action, defined as a sequence of primitive actions, an agent is able to bypass intermediate states to a farther state and facilitate its learning procedure.
Mixture of Step Returns in Bootstrapped DQN
Nevertheless, integrating step returns into a single target sacrifices the diversity of the advantages offered by different step return targets.
Toward Synergism in Macro Action Ensembles
Macro actions have been demonstrated to be beneficial for the learning processes of an agent.
Semantic Segmentation Based Unsupervised Domain Adaptation via Pseudo-Label Fusion
In this paper, we propose a pseudo label fusion framework (PLF), a learning framework developed to deal with the domain gap between a source domain and a target domain for performing semantic segmentation based UDA in the unseen target domain.
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
In fully cooperative multi-agent reinforcement learning (MARL) settings, the environments are highly stochastic due to the partial observability of each agent and the continuously changing policies of the other agents.
Ranked #1 on
SMAC
on SMAC 27m_vs_30m
Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptation
Recent researches on unsupervised domain adaptation (UDA) have demonstrated that end-to-end ensemble learning frameworks serve as a compelling option for UDA tasks.
Ranked #13 on
Unsupervised Domain Adaptation
on SYNTHIA-to-Cityscapes
Reducing the Deployment-Time Inference Control Costs of Deep Reinforcement Learning Agents via an Asymmetric Architecture
Deep reinforcement learning (DRL) has been demonstrated to provide promising results in several challenging decision making and control tasks.
Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding
This paper proposes a new self-attention based model for music score infilling, i. e., to generate a polyphonic music sequence that fills in the gap between given past and future contexts.
Investigation of Factorized Optical Flows as Mid-Level Representations
In this paper, we introduce a new concept of incorporating factorized flow maps as mid-level representations, for bridging the perception and the control modules in modular learning based robotic frameworks.
Denoising Likelihood Score Matching for Conditional Score-based Data Generation
These methods facilitate the training procedure of conditional score models, as a mixture of scores can be separately estimated using a score model and a classifier.
Pixel-Wise Prediction based Visual Odometry via Uncertainty Estimation
This paper introduces pixel-wise prediction based visual odometry (PWVO), which is a dense prediction task that evaluates the values of translation and rotation for every pixel in its input observations.
On Investigating the Conservative Property of Score-Based Generative Models
In addition, we show that USBMs' inability to preserve the property of conservativeness may lead to degraded performance in practice.
ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDA
Despite their effectiveness, using depth as domain invariant information in UDA tasks may lead to multiple issues, such as excessively high extraction costs and difficulties in achieving a reliable prediction quality.
Virtual Guidance as a Mid-level Representation for Navigation
In the context of autonomous navigation, effectively conveying abstract navigational cues to agents in dynamic environments poses challenges, particularly when the navigation information is multimodal.
Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution
Flow-based methods have demonstrated promising results in addressing the ill-posed nature of super-resolution (SR) by learning the distribution of high-resolution (HR) images with the normalizing flow.
Ranked #5 on
Image Super-Resolution
on DIV2K val - 4x upscaling
(using extra training data)
Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution
Implicit neural representation has recently shown a promising ability in representing images with arbitrary resolutions.
Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)
Addressing pose ambiguity in 6D object pose estimation from single RGB images presents a significant challenge, particularly due to object symmetries or occlusions.
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
In fully cooperative multi-agent reinforcement learning (MARL) settings, environments are highly stochastic due to the partial observability of each agent and the continuously changing policies of other agents.
Ranked #1 on
SMAC
on SMAC 26m_vs_30m
MVA2023 Small Object Detection Challenge for Spotting Birds: Dataset, Methods, and Results
Small Object Detection (SOD) is an important machine vision topic because (i) a variety of real-world applications require object detection for distant objects and (ii) SOD is a challenging task due to the noisy, blurred, and less-informative image appearances of small objects.
Ranked #2 on
Small Object Detection
on SOD4SB Public Test
(using extra training data)
Ensemble Fusion for Small Object Detection
Detecting small objects is often impeded by blurriness and low resolution, which poses substantial challenges for accurately detecting and localizing such objects.
Ranked #1 on
Small Object Detection
on SOD4SB Public Test
(using extra training data)
Visual Forecasting as a Mid-level Representation for Avoidance
The challenge of navigation in environments with dynamic objects continues to be a central issue in the study of autonomous agents.
Learning to Terminate in Object Navigation
This paper tackles the critical challenge of object navigation in autonomous navigation systems, particularly focusing on the problem of target approach and episode termination in environments with long optimal episode length in Deep Reinforcement Learning (DRL) based methods.
Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning
In this paper, we focus on single-demonstration imitation learning (IL), a practical approach for real-world applications where obtaining numerous expert demonstrations is costly or infeasible.
Boosting Flow-based Generative Super-Resolution Models via Learned Prior
This prior is a latent code predicted by our proposed latent module conditioned on the low-resolution image, which is then transformed by the flow model into an SR image.
Ranked #3 on
Image Super-Resolution
on DIV2K val - 4x upscaling
(using extra training data)
AdaIR: Exploiting Underlying Similarities of Image Restoration Tasks with Adapters
Towards this goal, we propose AdaIR, a novel framework that enables low storage cost and efficient training without sacrificing performance.
