Search Results for author:
Found 29 papers, 22 papers with code
Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning
PointGST freezes the pre-trained model and introduces a lightweight, trainable Point Cloud Spectral Adapter (PCSA) to fine-tune parameters in the spectral domain.
3D Parameter-Efficient Fine-Tuning for Classification
3D Point Cloud Classification
+3
Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression
Slow inference speed is one of the most crucial concerns for deploying multi-view 3D detectors to tasks with high real-time requirements like autonomous driving.
Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid
To address this issue, we introduce a Complementary Image Pyramid (CIP), a simple, effective, and plug-and-play solution designed to mitigate semantic discontinuity during high-resolution image processing.
A Unified Framework for 3D Scene Understanding
We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model.
SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection
Specifically, we observe that objects from aerial images are usually arbitrary orientations, small scales, and aggregation, which inspires the following core designs: a Simple Instance-aware Dense Sampling (SIDS) strategy is used to generate comprehensive dense pseudo-labels; the Geometry-aware Adaptive Weighting (GAW) loss dynamically modulates the importance of each pair between pseudo-label and corresponding prediction by leveraging the intricate geometric information of aerial objects; we treat aerial images as global layouts and explicitly build the many-to-many relationship between the sets of pseudo-labels and predictions via the proposed Noise-driven Global Consistency (NGC).
MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
The sparsely activated mixture of experts (MoE) model presents a promising alternative to traditional densely activated (dense) models, enhancing both quality and computational efficiency.
Anomaly Detection by Adapting a pre-trained Vision Language Model
Recently, large vision and language models have shown their success when adapting them to many downstream tasks.
Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis
To achieve this goal, we freeze the parameters of the default pre-trained models and then propose the Dynamic Adapter, which generates a dynamic scale for each token, considering the token significance to the downstream task.
3D Parameter-Efficient Fine-Tuning for Classification
Transfer Learning
AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene Understanding
For such purpose, this paper presents an advanced sampler that achieves both high accuracy and efficiency.
Ranked #2 on
3D Part Segmentation
on ShapeNet-Part
PointMamba: A Simple State Space Model for Point Cloud Analysis
Unlike traditional Transformers, PointMamba employs a linear complexity algorithm, presenting global modeling capacity while significantly reducing computational costs.
You Only Look Bottom-Up for Monocular 3D Object Detection
Monocular 3D Object Detection is an essential task for autonomous driving.
A Discrepancy Aware Framework for Robust Anomaly Detection
To alleviate this issue, we present a Discrepancy Aware Framework (DAF), which demonstrates robust performance consistently with simple and cheap strategies across different anomaly detection benchmarks.
Diffusion-based 3D Object Detection with Random Boxes
3D object detection is an essential task for achieving autonomous driving.
SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model
In the spirit of unleashing the capability of foundation models on vision tasks, the Segment Anything Model (SAM), a vision foundation model for image segmentation, has been proposed recently and presents strong zero-shot ability on many downstream 2D tasks.
Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution
We evaluate the existing end-to-end methods for VIE on the proposed dataset and observe that the performance of these methods has a distinguishable drop from SROIE (a widely used English dataset) to our proposed dataset due to the larger variance of layout and entities.
SOOD: Towards Semi-Supervised Oriented Object Detection
Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years.
CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model
To the best of our knowledge, CrowdCLIP is the first to investigate the vision language knowledge to solve the counting problem.
Ranked #1 on
Cross-Part Crowd Counting
on ShanghaiTech B
Super-Resolution Information Enhancement For Crowd Counting
As the proposed method requires SR labels, we further propose a Super-Resolution Crowd Counting dataset (SR-Crowd).
DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detection
In this paper, we present a simple yet effective semi-supervised 3D object detector named DDS3D.
A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection
Advanced 3D object detection methods usually rely on large-scale, elaborately labeled datasets to achieve good performance.
When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition
Recently, most handwritten mathematical expression recognition (HMER) methods adopt the encoder-decoder networks, which directly predict the markup sequences from formula images with the attention mechanism.
Comprehensive Benchmark Datasets for Amharic Scene Text Detection and Recognition
Ethiopic/Amharic script is one of the oldest African writing systems, which serves at least 23 languages (e. g., Amharic, Tigrinya) in East Africa for more than 120 million people.
An End-to-End Transformer Model for Crowd Localization
Crowd localization, predicting head positions, is a more practical and high-level task than simply counting.
LATFormer: Locality-Aware Point-View Fusion Transformer for 3D Shape Recognition
To investigate this, we propose a novel Locality-Aware Point-View Fusion Transformer (LATFormer) for 3D shape retrieval and classification.
VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint.
TransCrowd: weakly-supervised crowd counting with transformers
Current weakly-supervised counting methods adopt the CNN to regress a total count of the crowd by an image-to-count paradigm.
Focal Inverse Distance Transform Maps for Crowd Localization
Most regression-based methods utilize convolution neural networks (CNN) to regress a density map, which can not accurately locate the instance in the extremely dense scene, attributed to two crucial reasons: 1) the density map consists of a series of blurry Gaussian blobs, 2) severe overlaps exist in the dense region of the density map.
Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting
In this paper, we propose a simple yet efficient counting network based on point-level annotations.
AutoScale: Learning to Scale for Crowd Counting and Localization
A major issue is that the density map on dense regions usually accumulates density values from a number of nearby Gaussian blobs, yielding different large density values on a small set of pixels.
