Search Results for author:
Found 32 papers, 22 papers with code
Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling
In this paper, we focus on the compression of DETR with knowledge distillation.
Equalized Focal Loss for Dense Long-Tailed Object Detection
The conventional focal loss balances the training process with the same modulating factor for all categories, thus failing to handle the long-tailed problem.
RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features
In this work, we propose a new method called RefineMask for high-quality instance segmentation of objects and scenes, which incorporates fine-grained features during the instance-wise segmenting process in a multi-stage manner.
Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection
To address the problem of imbalanced gradients, we introduce a new version of equalization loss, called equalization loss v2 (EQL v2), a novel gradient guided reweighing mechanism that re-balances the training process for each category independently and equally.
Ranked #12 on
Instance Segmentation
on LVIS v1.0 val
Generative Adversarial Network with Spatial Attention for Face Attribute Editing
The generator contains an attribute manipulation network (AMN) to edit the face image, and a spatial attention network (SAN) to localize the attribute-specific region which restricts the alternation of AMN within this region.
CEDNet: A Cascade Encoder-Decoder Network for Dense Prediction
A hallmark of CEDNet is its ability to incorporate high-level features from early stages to guide low-level feature learning in subsequent stages, thereby enhancing the effectiveness of multi-scale feature fusion.
The Winning Solution to the iFLYTEK Challenge 2021 Cultivated Land Extraction from High-Resolution Remote Sensing Image
This report introduces our solution to the iFLYTEK challenge 2021 cultivated land extraction from high-resolution remote sensing image.
A Unified Continual Learning Framework with General Parameter-Efficient Tuning
1) Learning: the pre-trained model adapts to the new task by tuning an online PET module, along with our adaptation speed calibration to align different PET modules, 2) Accumulation: the task-specific knowledge learned by the online PET module is accumulated into an offline PET module through momentum update, 3) Ensemble: During inference, we respectively construct two experts with online/offline PET modules (which are favored by the novel/historical tasks) for prediction ensemble.
Dynamic Class Queue for Large Scale Face Recognition In the Wild
Since only a subset of classes is selected for each iteration, the computing requirement is reduced.
Ranked #3 on
Face Recognition
on AgeDB-30
HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds
To reduce computational costs, these methods resort to submanifold sparse convolutions, which prevent the information exchange among spatially disconnected features.
SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection
LiDAR-based 3D object detection plays an essential role in autonomous driving.
An Information Theory-inspired Strategy for Automatic Network Pruning
This practically limits the application of model compression when the model needs to be deployed on a wide range of devices.
UFO: Unified Feature Optimization
UFO aims to benefit each single task with a large-scale pretraining on all tasks.
Open-TransMind: A New Baseline and Benchmark for 1st Foundation Model Challenge of Intelligent Transportation
To address these, we designed the 1st Foundation Model Challenge, with the goal of increasing the popularity of foundation model technology in traffic scenarios and promoting the rapid development of the intelligent transportation industry.
Ranked #1 on
2D Object Detection
on CeyMo
CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation
LiDAR semantic segmentation essential for advanced autonomous driving is required to be accurate, fast, and easy-deployed on mobile platforms.
Ranked #12 on
Robust 3D Semantic Segmentation
on SemanticKITTI-C
VRP-SAM: SAM with Visual Reference Prompt
In this paper, we propose a novel Visual Reference Prompt (VRP) encoder that empowers the Segment Anything Model (SAM) to utilize annotated reference images as prompts for segmentation, creating the VRP-SAM model.
Center Focusing Network for Real-Time LiDAR Panoptic Segmentation
LiDAR panoptic segmentation facilitates an autonomous vehicle to comprehensively understand the surrounding objects and scenes and is required to run in real time.
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking.
Active Pointly-Supervised Instance Segmentation
In this paper, we present an economic active learning setting, named active pointly-supervised instance segmentation (APIS), which starts with box-level annotations and iteratively samples a point within the box and asks if it falls on the object.
Dual Relation Knowledge Distillation for Object Detection
By distilling the global pixel relation, the student detector can learn the relation between foreground and background features, and avoid the difficulty of distilling features directly for the feature imbalance issue.
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+.
Layered Rendering Diffusion Model for Zero-Shot Guided Image Synthesis
The LRDiff framework constructs an image-rendering process with multiple layers, each of which applies the vision guidance to instructively estimate the denoising direction for a single object.
1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask
This article introduces the solutions of the team lvisTraveler for LVIS Challenge 2020.
Ranked #1 on
Instance Segmentation
on LVIS v1.0 test-dev
Real Image Super Resolution Via Heterogeneous Model Ensemble using GP-NAS
With advancement in deep neural network (DNN), recent state-of-the-art (SOTA) image superresolution (SR) methods have achieved impressive performance using deep residual network with dense skip connections.
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.
AutoPruning for Deep Neural Network with Dynamic Channel Masking
In the process of pruning, we utilize a searchable hyperparameter, remaining ratio, to denote the number of channels in each convolution layer, and then a dynamic masking process is proposed to describe the corresponding channel evolution.
Coexistience of phononic six-fold, four-fold and three-fold excitations in ternary antimonide Zr3Ni3Sb4
However, these materials are uncommon because these excitations in electronic systems are usually broken by spin-orbit coupling (SOC) and normally far from the Fermi level.
Materials Science
EC-DARTS: Inducing Equalized and Consistent Optimization Into DARTS
EC-DARTS decouples different operations based on their categories to optimize the operation weights so that the operation gap between them is shrinked.
Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining
The training process consists of self-supervised pretraining and finetuning a ViT-Huge encoder on ImageNet-1K, pretraining the detector on Object365, and finally finetuning it on COCO.
Ranked #8 on
Object Detection
on COCO test-dev
Accelerating Vision Transformers Based on Heterogeneous Attention Patterns
On one hand, different images share more similar attention patterns in early layers than later layers, indicating that the dynamic query-by-key self-attention matrix may be replaced with a static self-attention matrix in early layers.
Revisiting Multi-modal 3D Semantic Segmentation in Real-world Autonomous Driving
LiDAR and camera are two critical sensors for multi-modal 3D semantic segmentation and are supposed to be fused efficiently and robustly to promise safety in various real-world scenarios.
FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective View
In autonomous driving, 3D occupancy prediction outputs voxel-wise status and semantic labels for more comprehensive understandings of 3D scenes compared with traditional perception tasks, such as 3D object detection and bird's-eye view (BEV) semantic segmentation.
