Search Results for author:
Found 39 papers, 22 papers with code
ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention
Recently, linear complexity sequence modeling networks have achieved modeling capabilities similar to Vision Transformers on a variety of computer vision tasks, while using fewer FLOPs and less memory.
POWQMIX: Weighted Value Factorization with Potentially Optimal Joint Actions Recognition for Cooperative Multi-Agent Reinforcement Learning
Value function factorization methods are commonly used in cooperative multi-agent reinforcement learning, with QMIX receiving significant attention.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning
Learning a human-like driving policy from large-scale driving demonstrations is promising, but the uncertainty and non-deterministic nature of planning make it challenging.
Circuit as Set of Points
In our work, we propose a novel perspective for circuit design by treating circuit components as point clouds and using Transformer-based point cloud perception methods to extract features from the circuit.
MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction
We propose a unified permutation-equivalent modeling approach, \ie, modeling map element as a point set with a group of equivalent permutations, which accurately describes the shape of map element and stabilizes the learning process.
Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery
In this paper, we propose a method to construct a boundary that discriminates safe and unsafe states.
VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scene
We design a divide-and-conquer annotation scheme to solve the spatial extensibility problem of HD map generation, and abstract map elements with a variety of geometric patterns as unified point sequence representation, which can be extended to most map elements in the driving scene.
VAD: Vectorized Scene Representation for Efficient Autonomous Driving
In this paper, we propose VAD, an end-to-end vectorized paradigm for autonomous driving, which models the driving scene as a fully vectorized representation.
Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction
Motivated by this, we propose to model the lane graph in a novel path-wise manner, which well preserves the continuity of the lane and encodes traffic information for planning.
Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Prediction
Motion prediction is highly relevant to the perception of dynamic objects and static map elements in the scenarios of autonomous driving.
A Many-ported and Shared Memory Architecture for High-Performance ADAS SoCs
A domain specific memory architecture is essential to achieve the above goals.
MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
High-definition (HD) map provides abundant and precise environmental information of the driving scene, serving as a fundamental and indispensable component for planning in autonomous driving system.
Ranked #7 on
3D Lane Detection
on OpenLane-V2 val
Polar Parametrization for Vision-based Surround-View 3D Detection
Based on Polar Parametrization, we propose a surround-view 3D DEtection TRansformer, named PolarDETR.
Sparse Instance Activation for Real-Time Instance Segmentation
In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation.
Ranked #7 on
Real-time Instance Segmentation
on MSCOCO
AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception
For segmentation, we integrate AziNorm into KPConv.
Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation
Based on deep networks, video object detection is actively studied for pushing the limits of detection speed and accuracy.
Diversity Transfer Network for Few-Shot Learning
The learning problem of the sample generation (i. e., diversity transfer) is solved via minimizing an effective meta-classification loss in a single-stage network, instead of the generative loss in previous works.
RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation
To reciprocate these two tasks, we design a two-stream structure to learn features on both the object level (i. e., bounding boxes) and the pixel level (i. e., instance masks) jointly.
Ranked #94 on
Instance Segmentation
on COCO test-dev
High Performance Visual Object Tracking with Unified Convolutional Networks
In this paper, we propose an end-to-end framework to learn the convolutional features and perform the tracking process simultaneously, namely, a unified convolutional tracker (UCT).
Object Detection in Video with Spatial-temporal Context Aggregation
Without any bells and whistles, our method obtains 80. 3\% mAP on the ImageNet VID dataset, which is superior over the previous state-of-the-arts.
Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation
Video object segmentation (VOS) aims at pixel-level object tracking given only the annotations in the first frame.
Ranked #1 on
Visual Object Tracking
on YouTube-VOS 2018
(Jaccard (Seen) metric)
Mask Scoring R-CNN
In this paper, we study this problem and propose Mask Scoring R-CNN which contains a network block to learn the quality of the predicted instance masks.
Ranked #75 on
Instance Segmentation
on COCO minival
EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search
In our implementations, architectures are first searched on a small dataset, e. g., CIFAR-10.
Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-identification
We propose a novel deep network called Mancs that solves the person re-identification problem from the following aspects: fully utilizing the attention mechanism for the person misalignment problem and properly sampling for the ranking loss to obtain more stable person representation.
Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking
The separation of the task requires to define a hand-crafted training goal in affinity learning stage and a hand-crafted cost function of data association stage, which prevents the tracking goals from learning directly from the feature.
Reinforced Evolutionary Neural Architecture Search
To address this issue, we propose the Reinforced Evolutionary Neural Architecture Search (RE- NAS), which is an evolutionary method with the reinforced mutation for NAS.
Unsupervised Domain Adaptive Re-Identification: Theory and Practice
We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation.
Ranked #16 on
Unsupervised Domain Adaptation
on Market to Duke
Elements of Effective Deep Reinforcement Learning towards Tactical Driving Decision Making
Tactical driving decision making is crucial for autonomous driving systems and has attracted considerable interest in recent years.
UCT: Learning Unified Convolutional Networks for Real-time Visual Tracking
Convolutional neural networks (CNN) based tracking approaches have shown favorable performance in recent benchmarks.
Text Flow: A Unified Text Detection System in Natural Scene Images
With character candidates detected by cascade boosting, the min-cost flow network model integrates the last three sequential steps into a single process which solves the error accumulation problem at both character level and text line level effectively.
CNN-RNN: A Unified Framework for Multi-label Image Classification
While deep convolutional neural networks (CNNs) have shown a great success in single-label image classification, it is important to note that real world images generally contain multiple labels, which could correspond to different objects, scenes, actions and attributes in an image.
A Deep Visual Correspondence Embedding Model for Stereo Matching Costs
This paper presents a data-driven matching cost for stereo matching.
Look and Think Twice: Capturing Top-Down Visual Attention With Feedback Convolutional Neural Networks
While feedforward deep convolutional neural networks (CNNs) have been a great success in computer vision, it is important to remember that the human visual contex contains generally more feedback connections than foward connections.
Targeting Ultimate Accuracy: Face Recognition via Deep Embedding
Face Recognition has been studied for many decades.
Multi-Objective Convolutional Learning for Face Labeling
This paper formulates face labeling as a conditional random field with unary and pairwise classifiers.
Deep Multiple Instance Learning for Image Classification and Auto-Annotation
The recent development in learning deep representations has demonstrated its wide applications in traditional vision tasks like classification and detection.
Learning From Massive Noisy Labeled Data for Image Classification
To demonstrate the effectiveness of our approach, we collect a large-scale real-world clothing classification dataset with both noisy and clean labels.
Conditional Random Fields as Recurrent Neural Networks
Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding.
Ranked #36 on
Semantic Segmentation
on PASCAL VOC 2012 test
Large Scale Strongly Supervised Ensemble Metric Learning, with Applications to Face Verification and Retrieval
Learning Mahanalobis distance metrics in a high- dimensional feature space is very difficult especially when structural sparsity and low rank are enforced to improve com- putational efficiency in testing phase.
