Search Results for author: Jihan Yang

Found 14 papers, 10 papers with code

Can 3D Vision-Language Models Truly Understand Natural Language?

1 code implementation21 Mar 2024 Weipeng Deng, Runyu Ding, Jihan Yang, Jiahui Liu, Yijiang Li, Xiaojuan Qi, Edith Ngai

To test the language understandability of 3D-VL models, we first propose a language robustness task for systematically assessing 3D-VL models across various tasks, benchmarking their performance when presented with different language style variants.


V-IRL: Grounding Virtual Intelligence in Real Life

1 code implementation5 Feb 2024 Jihan Yang, Runyu Ding, Ellis Brown, Xiaojuan Qi, Saining Xie

There is a sensory gulf between the Earth that humans inhabit and the digital realms in which modern AI agents are created.

Decision Making

Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding

no code implementations1 Aug 2023 Runyu Ding, Jihan Yang, Chuhui Xue, Wenqing Zhang, Song Bai, Xiaojuan Qi

To address this challenge, we propose to harness pre-trained vision-language (VL) foundation models that encode extensive knowledge from image-text pairs to generate captions for multi-view images of 3D scenes.

3D Open-Vocabulary Instance Segmentation Instance Segmentation +4

RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding

no code implementations3 Apr 2023 Jihan Yang, Runyu Ding, Zhe Wang, Xiaojuan Qi

Existing 3D scene understanding tasks have achieved high performance on close-set benchmarks but fail to handle novel categories in real-world applications.

Contrastive Learning Instance Segmentation +2

Towards Efficient 3D Object Detection with Knowledge Distillation

1 code implementation30 May 2022 Jihan Yang, Shaoshuai Shi, Runyu Ding, Zhe Wang, Xiaojuan Qi

Then, we build a benchmark to assess existing KD methods developed in the 2D domain for 3D object detection upon six well-constructed teacher-student pairs.

3D Object Detection Knowledge Distillation +3

ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection

no code implementations15 Aug 2021 Jihan Yang, Shaoshuai Shi, Zhe Wang, Hongsheng Li, Xiaojuan Qi

These specific designs enable the detector to be trained on meticulously refined pseudo labeled target data with denoised training signals, and thus effectively facilitate adapting an object detector to a target domain without requiring annotations.

3D Object Detection Data Augmentation +5

Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation

1 code implementation ICCV 2021 Ruifei He, Jihan Yang, Xiaojuan Qi

In this paper, we present a simple and yet effective Distribution Alignment and Random Sampling (DARS) method to produce unbiased pseudo labels that match the true class distribution estimated from the labeled data.

Data Augmentation Segmentation +1

ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection

1 code implementation CVPR 2021 Jihan Yang, Shaoshuai Shi, Zhe Wang, Hongsheng Li, Xiaojuan Qi

Then, the detector is iteratively improved on the target domain by alternatively conducting two steps, which are the pseudo label updating with the developed quality-aware triplet memory bank and the model training with curriculum data augmentation.

3D Object Detection Data Augmentation +4

PV-RCNN: The Top-Performing LiDAR-only Solutions for 3D Detection / 3D Tracking / Domain Adaptation of Waymo Open Dataset Challenges

1 code implementation28 Aug 2020 Shaoshuai Shi, Chaoxu Guo, Jihan Yang, Hongsheng Li

In this technical report, we present the top-performing LiDAR-only solutions for 3D detection, 3D tracking and domain adaptation three tracks in Waymo Open Dataset Challenges 2020.

3D Object Detection Domain Adaptation +1

An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation

no code implementations18 Dec 2019 Jihan Yang, Ruijia Xu, Ruiyu Li, Xiaojuan Qi, Xiaoyong Shen, Guanbin Li, Liang Lin

In contrast to adversarial alignment, we propose to explicitly train a domain-invariant classifier by generating and defensing against pointwise feature space adversarial perturbations.

Position Segmentation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.