Search Results for author:
Found 22 papers, 9 papers with code
S4-Driver: Scalable Self-Supervised Driving Multimodal Large Language Modelwith Spatio-Temporal Visual Representation
Many end-to-end approaches rely on human annotations to learn intermediate perception and prediction tasks, while purely self-supervised approaches--which directly learn from sensor inputs to generate planning trajectories without human annotations often underperform the state of the art.
S4-Driver: Scalable Self-Supervised Driving Multimodal Large Language Model with Spatio-Temporal Visual Representation
Many end-to-end approaches rely on human annotations to learn intermediate perception and prediction tasks, while purely self-supervised approaches--which directly learn from sensor inputs to generate planning trajectories without human annotations--often underperform the state of the art.
DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes
We present DeSiRe-GS, a self-supervised gaussian splatting representation, enabling effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios.
X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarios
Recent advancements have exploited diffusion models for the synthesis of either LiDAR point clouds or camera image data in driving scenarios.
TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection
Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets.
Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning
The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning.
RoadBEV: Road Surface Reconstruction in Bird's Eye View
This paper uniformly proposes two simple yet effective models for road elevation reconstruction in BEV named RoadBEV-mono and RoadBEV-stereo, which estimate road elevation with monocular and stereo images, respectively.
Boundary Matters: A Bi-Level Active Finetuning Framework
In this paper, we propose a Bi-Level Active Finetuning framework to select the samples for annotation in one shot, which includes two stages: core sample selection for diversity, and boundary sample selection for uncertainty.
ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving
End-to-end differentiable learning for autonomous driving (AD) has recently become a prominent paradigm.
Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach
In the long-tailed recognition field, the Decoupled Training paradigm has demonstrated remarkable capabilities among various methods.
Cohere3D: Exploiting Temporal Coherence for Unsupervised Representation Learning of Vision-based Autonomous Driving
Observations from different angles enable the recovery of 3D object states from 2D image inputs if we can identify the same instance in different input frames.
Towards Free Data Selection with General-Purpose Models
However, current approaches, represented by active learning methods, typically follow a cumbersome pipeline that iterates the time-consuming model training and batch data selection repeatedly.
SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection
However, given that objects occupy only a small part of a scene, finding dense candidates and generating dense representations is noisy and inefficient.
Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm
We propose a novel method called ActiveFT for active finetuning task to select a subset of data distributing similarly with the entire unlabeled pool and maintaining enough diversity by optimizing a parametric model in the continuous space.
Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning
Experimental results demonstrate that our proposed method achieves policy generalization to unseen compositional tasks in a zero-shot manner.
Towards General and Efficient Active Learning
Existing work follows a cumbersome pipeline that repeats the time-consuming model training and batch data selection multiple times.
Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds
To date, various 3D scene understanding tasks still lack practical and generalizable pre-trained models, primarily due to the intricate nature of 3D scene understanding tasks and their immense variations introduced by camera views, lighting, occlusions, etc.
Ranked #5 on
3D Object Detection
on SUN-RGBD
Towards Understanding and Improving Dropout in Game Theory
Experimental results on various DNNs and datasets have shown that the interaction loss can effectively improve the utility of dropout and boost the performance of DNNs.
Interpreting Multivariate Shapley Interactions in DNNs
In this paper, we define and quantify the significance of interactions among multiple input variables of the DNN.
DecAug: Augmenting HOI Detection via Decomposition
Human-object interaction (HOI) detection requires a large amount of annotated data.
Ranked #77 on
Domain Generalization
on PACS
DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection
On the other hand, existing one-stage methods mainly focus on the union regions of interactions, which introduce unnecessary visual information as disturbances to HOI detection.
Ranked #15 on
Human-Object Interaction Detection
on V-COCO
Interpreting and Boosting Dropout from a Game-Theoretic View
This paper aims to understand and improve the utility of the dropout operation from the perspective of game-theoretic interactions.
