230 citations · 804 across the 33 of their papers we have counts for
33 papers
LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model
Senqiao Yang, Tianyuan Qu, Xin Lai +4
While LISA effectively bridges the gap between segmentation and large language models to enable reasoning segmentation, it poses certain limitations: unable to distinguish differen…
BAL: Balancing Diversity and Novelty for Active Learning
Jingyao Li, Pengguang Chen, Shaozuo Yu +2
The objective of Active Learning is to strategically label a subset of the dataset to maximize performance within a predetermined labeling budget. In this study, we harness feature…
Prompt Highlighter: Interactive Control for Multi-Modal LLMs
Yuechen Zhang, Shengju Qian, Bohao Peng +2
This study targets a critical aspect of multi-modal LLMs' (LLMs&VLMs) inference: explicit controllable text generation. Multi-modal LLMs empower multi-modality understanding with t…
Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields
Tao Hu, Xiaogang Xu, Shu Liu +1
Synthesizing photo-realistic images from a point cloud is challenging because of the sparsity of point cloud representation. Recent Neural Radiance Fields and extensions are propos…
EfficientNeRF: Efficient Neural Radiance Fields
Tao Hu, Shu Liu, Yilun Chen +2
Neural Radiance Fields (NeRF) has been wildly applied to various tasks for its high-quality representation of 3D scenes. It takes long per-scene training time and per-image testing…
DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors
Yilun Chen, Shijia Huang, Shu Liu +2
Camera-based 3D object detectors are welcome due to their wider deployment and lower price than LiDAR sensors. We first revisit the prior stereo detector DSGN for its stereo volume…
Stratified Transformer for 3D Point Cloud Segmentation
Xin Lai, Jianhui Liu, Li Jiang +5
3D point cloud segmentation has made tremendous progress in recent years. Most current methods focus on aggregating local features, but fail to directly model long-range dependenci…
SEA: Bridging the Gap Between One- and Two-stage Detector Distillation via SEmantic-aware Alignment
Yixin Chen, Zhuotao Tian, Pengguang Chen +2
We revisit the one- and two-stage detector distillation tasks and present a simple and efficient semantic-aware framework to fill the gap between them. We address the pixel-level i…
Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation
Li Jiang, Shaoshuai Shi, Zhuotao Tian +4
Rapid progress in 3D semantic segmentation is inseparable from the advances of deep network models, which highly rely on large-scale annotated data for training. To address the hig…
Deep Structured Instance Graph for Distilling Object Detectors
Yixin Chen, Pengguang Chen, Shu Liu +2
Effectively structuring deep knowledge plays a pivotal role in transfer from teacher to student, especially in semantic vision tasks. In this paper, we present a simple knowledge s…
Exploring and Improving Mobile Level Vision Transformers
Pengguang Chen, Yixin Chen, Shu Liu +2
We study the vision transformer structure in the mobile level in this paper, and find a dramatic performance drop. We analyze the reason behind this phenomenon, and propose a novel…
Parametric Contrastive Learning
Jiequan Cui, Zhisheng Zhong, Shu Liu +2
In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed recognition. Based on theoretical analysis, we observe supervised contrastive loss tends to b…
Semi-supervised Semantic Segmentation with Directional Context-aware Consistency
Xin Lai, Zhuotao Tian, Li Jiang +4
Semantic segmentation has made tremendous progress in recent years. However, satisfying performance highly depends on a large number of pixel-level annotations. Therefore, in this…
Distilling Knowledge via Knowledge Review
Pengguang Chen, Shu Liu, Hengshuang Zhao +1
Knowledge distillation transfers knowledge from the teacher network to the student one, with the goal of greatly improving the performance of the student network. Previous methods…
Improving Calibration for Long-Tailed Recognition
Zhisheng Zhong, Jiequan Cui, Shu Liu +1
Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and classifier learning to…
Jigsaw Clustering for Unsupervised Visual Representation Learning
Pengguang Chen, Shu Liu, Jiaya Jia
Unsupervised representation learning with contrastive learning achieved great success. This line of methods duplicate each training batch to construct contrastive pairs, making eac…
Video Instance Segmentation with a Propose-Reduce Paradigm
Huaijia Lin, Ruizheng Wu, Shu Liu +2
Video instance segmentation (VIS) aims to segment and associate all instances of predefined classes for each frame in videos. Prior methods usually obtain segmentation for a frame…
ResLT: Residual Learning for Long-tailed Recognition
Jiequan Cui, Shu Liu, Zhuotao Tian +2
Deep learning algorithms face great challenges with long-tailed data distribution which, however, is quite a common case in real-world scenarios. Previous methods tackle the proble…
Learnable Boundary Guided Adversarial Training
Jiequan Cui, Shu Liu, Liwei Wang +1
Previous adversarial training raises model robustness under the compromise of accuracy on natural data. In this paper, we reduce natural accuracy degradation. We use the model logi…
Generalized Few-shot Semantic Segmentation
Zhuotao Tian, Xin Lai, Li Jiang +4
Training semantic segmentation models requires a large amount of finely annotated data, making it hard to quickly adapt to novel classes not satisfying this condition. Few-Shot Seg…
Dive Deeper Into Box for Object Detection
Ran Chen, Yong Liu, Mengdan Zhang +3
Anchor free methods have defined the new frontier in state-of-the-art object detection researches where accurate bounding box estimation is the key to the success of these methods.…
Jointly Modeling Aspect and Sentiment with Dynamic Heterogeneous Graph Neural Networks
Shu Liu, Wei Li, Yunfang Wu +2
Target-Based Sentiment Analysis aims to detect the opinion aspects (aspect extraction) and the sentiment polarities (sentiment detection) towards them. Both the previous pipeline a…
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
Li Jiang, Hengshuang Zhao, Shaoshuai Shi +3
Instance segmentation is an important task for scene understanding. Compared to the fully-developed 2D, 3D instance segmentation for point clouds have much room to improve. In this…
3DSSD: Point-based 3D Single Stage Object Detector
Zetong Yang, Yanan Sun, Shu Liu +1
Currently, there have been many kinds of voxel-based 3D single stage detectors, while point-based single stage methods are still underexplored. In this paper, we first present a li…