Search Results for author:
Found 51 papers, 15 papers with code
Offline Reinforcement Learning with Closed-Form Policy Improvement Operators
Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning.
Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification
To this end, we build a dual-branch network architecture based upon a modified Vision Transformer (ViT).
OneFormer: One Transformer to Rule Universal Image Segmentation
However, such panoptic architectures do not truly unify image segmentation because they need to be trained individually on the semantic, instance, or panoptic segmentation to achieve the best performance.
Ranked #1 on
Semantic Segmentation
on Mapillary val
Learning Physical Dynamics with Subequivariant Graph Neural Networks
Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics.
Dynamics-Aware Spatiotemporal Occupancy Prediction in Urban Environments
Detection and segmentation of moving obstacles, along with prediction of the future occupancy states of the local environment, are essential for autonomous vehicles to proactively make safe and informed decisions.
DRAMA: Joint Risk Localization and Captioning in Driving
We make this data available to the community for further research.
VMFormer: End-to-End Video Matting with Transformer
In this paper, we propose VMFormer: a transformer-based end-to-end method for video matting.
Interaction Modeling with Multiplex Attention
Modeling multi-agent systems requires understanding how agents interact.
EvolveHypergraph: Group-Aware Dynamic Relational Reasoning for Trajectory Prediction
While the modeling of pair-wise relations has been widely studied in multi-agent interacting systems, its ability to capture higher-level and larger-scale group-wise activities is limited.
Point-to-Box Network for Accurate Object Detection via Single Point Supervision
However, the performance gap between point supervised object detection (PSOD) and bounding box supervised detection remains large.
Causal Balancing for Domain Generalization
While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations.
Symbolic Expression Transformer: A Computer Vision Approach for Symbolic Regression
Symbolic Regression (SR) is a type of regression analysis to automatically find the mathematical expression that best fits the data.
Neighborhood Attention Transformer
We present Neighborhood Attention (NA), the first efficient and scalable sliding-window attention mechanism for vision.
Ranked #86 on
Semantic Segmentation
on ADE20K
BCOT: A Markerless High-Precision 3D Object Tracking Benchmark
Our new benchmark dataset contains 20 textureless objects, 22 scenes, 404 video sequences and 126K images captured in real scenes.
Important Object Identification with Semi-Supervised Learning for Autonomous Driving
We propose a novel approach for important object identification in egocentric driving scenarios with relational reasoning on the objects in the scene.
ConvNeXt-backbone HoVerNet for nuclei segmentation and classification
This manuscript gives a brief description of the algorithm used to participate in CoNIC Challenge 2022.
Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification
Assisted with the camera-aware proxies, we design two proxy-level contrastive learning losses that are, respectively, based on offline and online association results.
Multi-Objective Diverse Human Motion Prediction With Knowledge Distillation
Obtaining accurate and diverse human motion prediction is essential to many industrial applications, especially robotics and autonomous driving.
Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint
Unsupervised image-to-image (I2I) translation aims to learn a domain mapping function that can preserve the semantics of the input images without paired data.
SeMask: Semantically Masked Transformers for Semantic Segmentation
To achieve this, we propose SeMask, a simple and effective framework that incorporates semantic information into the encoder with the help of a semantic attention operation.
Ranked #5 on
Semantic Segmentation
on Cityscapes val
Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction
Improving the sample efficiency of reinforcement learning algorithms requires effective exploration.
SS-MAIL: Self-Supervised Multi-Agent Imitation Learning
We show that our method (SS-MAIL) outperforms prior state-of-the-art methods on real-world prediction tasks, as well as on custom-designed synthetic experiments.
Grouptron: Dynamic Multi-Scale Graph Convolutional Networks for Group-Aware Dense Crowd Trajectory Forecasting
Accurate, long-term forecasting of pedestrian trajectories in highly dynamic and interactive scenes is a long-standing challenge.
ConvMLP: Hierarchical Convolutional MLPs for Vision
MLP-based architectures, which consist of a sequence of consecutive multi-layer perceptron blocks, have recently been found to reach comparable results to convolutional and transformer-based methods.
Ranked #7 on
Image Classification
on Flowers-102
(using extra training data)
LOKI: Long Term and Key Intentions for Trajectory Prediction
We also propose a model that jointly performs trajectory and intention prediction, showing that recurrently reasoning about intention can assist with trajectory prediction.
RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting
Motion forecasting plays a significant role in various domains (e. g., autonomous driving, human-robot interaction), which aims to predict future motion sequences given a set of historical observations.
Orientation-Aware Planning for Parallel Task Execution of Omni-Directional Mobile Robot
Omni-directional mobile robot (OMR) systems have been very popular in academia and industry for their superb maneuverability and flexibility.
Autonomous Driving Strategies at Intersections: Scenarios, State-of-the-Art, and Future Outlooks
Due to the complex and dynamic character of intersection scenarios, the autonomous driving strategy at intersections has been a difficult problem and a hot point in the research of intelligent transportation systems in recent years.
MSN: Efficient Online Mask Selection Network for Video Instance Segmentation
Our method improves the masks from segmentation and propagation branches in an online manner using the Mask Selection Network (MSN) hence limiting the noise accumulation during mask tracking.
Ranked #12 on
Video Instance Segmentation
on YouTube-VIS validation
Spectral Temporal Graph Neural Network for Trajectory Prediction
To this end, we propose a Spectral Temporal Graph Neural Network (SpecTGNN), which can capture inter-agent correlations and temporal dependency simultaneously in frequency domain in addition to time domain.
RSCA: Real-time Segmentation-based Context-Aware Scene Text Detection
Segmentation-based scene text detection methods have been widely adopted for arbitrary-shaped text detection recently, since they make accurate pixel-level predictions on curved text instances and can facilitate real-time inference without time-consuming processing on anchors.
Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection
Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based models that are supported by well-designed assignment methods based on the Intersection-over-Union~(IoU) metric.
Escaping the Big Data Paradigm with Compact Transformers
Our models are flexible in terms of model size, and can have as little as 0. 28M parameters while achieving competitive results.
Ranked #1 on
Image Classification
on Flowers-102
(using extra training data)
Fine-Grained Image Classification
Superpixel Image Classification
Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking
Due to the existence of frequent interactions and uncertainty in the scene evolution, it is desired for the prediction system to enable relational reasoning on different entities and provide a distribution of future trajectories for each agent.
Minimal Geometry-Distortion Constraint for Unsupervised Image-to-Image Translation
Unsupervised image-to-image (I2I) translation, which aims to learn a domain mapping function without paired data, is very challenging because the function is highly under-constrained.
Shared Cross-Modal Trajectory Prediction for Autonomous Driving
At test time, a single input modality (e. g., LiDAR data) is required to generate predictions from the input perspective (i. e., in the LiDAR space), while taking advantages from the model trained with multiple sensor modalities.
Reinforcement Learning for Autonomous Driving with Latent State Inference and Spatial-Temporal Relationships
Deep reinforcement learning (DRL) provides a promising way for learning navigation in complex autonomous driving scenarios.
Shared Cross-Modal Trajectory Prediction for Autonomous Driving
At test time, a single input modality (e. g., LiDAR data) is required to generate predictions from the input perspective (i. e., in the LiDAR space), while taking advantages from the model trained with multiple sensor modalities.
EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning
In this paper, we propose a generic trajectory forecasting framework (named EvolveGraph) with explicit relational structure recognition and prediction via latent interaction graphs among multiple heterogeneous, interactive agents.
Ranked #10 on
Trajectory Prediction
on Stanford Drone
Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network
Effective understanding of the environment and accurate trajectory prediction of surrounding dynamic obstacles are indispensable for intelligent mobile systems (like autonomous vehicles and social robots) to achieve safe and high-quality planning when they navigate in highly interactive and crowded scenarios.
Multi-task Batch Reinforcement Learning with Metric Learning
To perform well, the policy must infer the task identity from collected transitions by modelling its dependency on states, actions and rewards.
SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems
Object detection and tracking are challenging tasks for resource-constrained embedded systems.
Generic Tracking and Probabilistic Prediction Framework and Its Application in Autonomous Driving
The framework can incorporate an arbitrary prediction model as the implicit proposal distribution of the CMSMC method.
SkyNet: A Champion Model for DAC-SDC on Low Power Object Detection
Developing artificial intelligence (AI) at the edge is always challenging, since edge devices have limited computation capability and memory resources but need to meet demanding requirements, such as real-time processing, high throughput performance, and high inference accuracy.
Conditional Generative Neural System for Probabilistic Trajectory Prediction
Effective understanding of the environment and accurate trajectory prediction of surrounding dynamic obstacles are critical for intelligent systems such as autonomous vehicles and wheeled mobile robotics navigating in complex scenarios to achieve safe and high-quality decision making, motion planning and control.
Ranked #12 on
Trajectory Prediction
on Stanford Drone
Coordination and Trajectory Prediction for Vehicle Interactions via Bayesian Generative Modeling
In order to tackle the task of probabilistic prediction for multiple, interactive entities, we propose a coordination and trajectory prediction system (CTPS), which has a hierarchical structure including a macro-level coordination recognition module and a micro-level subtle pattern prediction module which solves a probabilistic generation task.
Text Guided Person Image Synthesis
This paper presents a novel method to manipulate the visual appearance (pose and attribute) of a person image according to natural language descriptions.
Interaction-aware Multi-agent Tracking and Probabilistic Behavior Prediction via Adversarial Learning
In order to enable high-quality decision making and motion planning of intelligent systems such as robotics and autonomous vehicles, accurate probabilistic predictions for surrounding interactive objects is a crucial prerequisite.
Weakly Supervised Scene Parsing with Point-based Distance Metric Learning
Semantic scene parsing is suffering from the fact that pixel-level annotations are hard to be collected.
Towards a Fatality-Aware Benchmark of Probabilistic Reaction Prediction in Highly Interactive Driving Scenarios
Modified methods based on PGM, NN and IRL are provided to generate probabilistic reaction predictions in an exemplar scenario of nudging from a highway ramp.
Generic Probabilistic Interactive Situation Recognition and Prediction: From Virtual to Real
Accurate and robust recognition and prediction of traffic situation plays an important role in autonomous driving, which is a prerequisite for risk assessment and effective decision making.
