205 citations · 784 across the 26 of their papers we have counts for
25 papers
GenAD: Generalized Predictive Model for Autonomous Driving
Jiazhi Yang, Shenyuan Gao, Yihang Qiu +11
In this paper, we introduce the first large-scale video prediction model in the autonomous driving discipline. To eliminate the restriction of high-cost data collection and empower…
LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving
Tianyu Li, Peijin Jia, Bangjun Wang +4
A map, as crucial information for downstream applications of an autonomous driving system, is usually represented in lanelines or centerlines. However, existing literature on map l…
DriveLM: Driving with Graph Visual Question Answering
Chonghao Sima, Katrin Renz, Kashyap Chitta +7
We study how vision-language models (VLMs) trained on web-scale data can be integrated into end-to-end driving systems to boost generalization and enable interactivity with human u…
DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving
Xiaosong Jia, Yulu Gao, Li Chen +3
End-to-end autonomous driving aims to build a fully differentiable system that takes raw sensor data as inputs and directly outputs the planned trajectory or control signals of the…
Detection Transformer with Stable Matching
Shilong Liu, Tianhe Ren, Jiayu Chen +8
This paper is concerned with the matching stability problem across different decoder layers in DEtection TRansformers (DETR). We point out that the unstable matching in DETR is cau…
Sparse Dense Fusion for 3D Object Detection
Yulu Gao, Chonghao Sima, Shaoshuai Shi +3
With the prevalence of multimodal learning, camera-LiDAR fusion has gained popularity in 3D object detection. Although multiple fusion approaches have been proposed, they can be cl…
Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking
Peng Gao, Renrui Zhang, Rongyao Fang +4
Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decod…
Planning-oriented Autonomous Driving
Yihan Hu, Jiazhi Yang, Li Chen +13
Modern autonomous driving system is characterized as modular tasks in sequential order, i.e., perception, prediction, and planning. In order to perform a wide diversity of tasks an…
Stare at What You See: Masked Image Modeling without Reconstruction
Hongwei Xue, Peng Gao, Hongyang Li +4
Masked Autoencoders (MAE) have been prevailing paradigms for large-scale vision representation pre-training. By reconstructing masked image patches from a small portion of visible…
Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
Hongyang Li, Chonghao Sima, Jifeng Dai +19
Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending and drawing extensive attention both from industry and academia. Conventional approaches…
BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers
Zhiqi Li, Wenhai Wang, Hongyang Li +5
3D visual perception tasks, including 3D detection and map segmentation based on multi-camera images, are essential for autonomous driving systems. In this work, we present a new f…
PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
Li Chen, Chonghao Sima, Yang Li +8
Methods for 3D lane detection have been recently proposed to address the issue of inaccurate lane layouts in many autonomous driving scenarios (uphill/downhill, bump, etc.). Previo…
Exploring intermediate representation for monocular vehicle pose estimation
Shichao Li, Zengqiang Yan, Hongyang Li +1
We present a new learning-based framework to recover vehicle pose in SO(3) from a single RGB image. In contrast to previous works that map from local appearance to observation angl…
Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
Hongyang Li, David Eigen, Samuel Dodge +2
Few-shot learning is an important area of research. Conceptually, humans are readily able to understand new concepts given just a few examples, while in more pragmatic terms, limit…
Feature Intertwiner for Object Detection
Hongyang Li, Bo Dai, Shaoshuai Shi +2
A well-trained model should classify objects with a unanimous score for every category. This requires the high-level semantic features should be as much alike as possible among sam…
Neural Network Encapsulation
Hongyang Li, Xiaoyang Guo, Bo Dai +2
A capsule is a collection of neurons which represents different variants of a pattern in the network. The routing scheme ensures only certain capsules which resemble lower counterp…
Rethinking Feature Discrimination and Polymerization for Large-scale Recognition
Yu Liu, Hongyang Li, Xiaogang Wang
Feature matters. How to train a deep network to acquire discriminative features across categories and polymerized features within classes has always been at the core of many comput…
Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection
Hongyang Li, Yu Liu, Wanli Ouyang +1
In this paper, we propose a zoom-out-and-in network for generating object proposals. A key observation is that it is difficult to classify anchors of different sizes with the same…
Recurrent Scale Approximation for Object Detection in CNN
Yu Liu, Hongyang Li, Junjie Yan +3
Since convolutional neural network (CNN) lacks an inherent mechanism to handle large scale variations, we always need to compute feature maps multiple times for multi-scale object…
Learning Deep Features via Congenerous Cosine Loss for Person Recognition
Yu Liu, Hongyang Li, Xiaogang Wang
Person recognition aims at recognizing the same identity across time and space with complicated scenes and similar appearance. In this paper, we propose a novel method to address t…
Zoom Out-and-In Network with Recursive Training for Object Proposal
Hongyang Li, Yu Liu, Wanli Ouyang +1
In this paper, we propose a zoom-out-and-in network for generating object proposals. We utilize different resolutions of feature maps in the network to detect object instances of v…
Dual Deep Network for Visual Tracking
Zhizhen Chi, Hongyang Li, Huchuan Lu +1
Visual tracking addresses the problem of identifying and localizing an unknown target in a video given the target specified by a bounding box in the first frame. In this paper, we…
Multi-Bias Non-linear Activation in Deep Neural Networks
Hongyang Li, Wanli Ouyang, Xiaogang Wang
As a widely used non-linear activation, Rectified Linear Unit (ReLU) separates noise and signal in a feature map by learning a threshold or bias. However, we argue that the classif…
LCNN: Low-level Feature Embedded CNN for Salient Object Detection
Hongyang Li, Huchuan Lu, Zhe Lin +2
In this paper, we propose a novel deep neural network framework embedded with low-level features (LCNN) for salient object detection in complex images. We utilise the advantage of…