Search Results for author:
Found 29 papers, 20 papers with code
Denoising Diffusion Step-aware Models
Denoising Diffusion Probabilistic Models (DDPMs) have garnered popularity for data generation across various domains.
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
LongLoRA adopts LLaMA2 7B from 4k context to 100k, or LLaMA2 70B to 32k on a single 8x A100 machine.
Mask-Attention-Free Transformer for 3D Instance Segmentation
Therefore, we abandon the mask attention design and resort to an auxiliary center regression task instead.
FocalFormer3D : Focusing on Hard Instance for 3D Object Detection
For 3D object detection, we instantiate this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects and improving prediction recall.
Ranked #8 on
3D Object Detection
on nuScenes
LISA: Reasoning Segmentation via Large Language Model
In this work, we propose a new segmentation task -- reasoning segmentation.
IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation
Category-level 6D pose estimation aims to predict the poses and sizes of unseen objects from a specific category.
Spherical Transformer for LiDAR-based 3D Recognition
In this work, we study the varying-sparsity distribution of LiDAR points and present SphereFormer to directly aggregate information from dense close points to the sparse distant ones.
Ranked #1 on
Semantic Segmentation
on KITTI Semantic Segmentation
VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking
Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies.
Ranked #1 on
3D Object Detection
on Argoverse2
FocalFormer3D: Focusing on Hard Instance for 3D Object Detection
For 3D object detection, we instantiate this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects and improving prediction recall.
Spatial Pruned Sparse Convolution for Efficient 3D Object Detection
3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects.
LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs
Recent advance in 2D CNNs has revealed that large kernels are important.
Voxel Field Fusion for 3D Object Detection
In this work, we present a conceptually simple yet effective framework for cross-modality 3D object detection, named voxel field fusion.
Focal Sparse Convolutional Networks for 3D Object Detection
In this paper, we introduce two new modules to enhance the capability of Sparse CNNs, both are based on making feature sparsity learnable with position-wise importance prediction.
When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search
TNAS performs a modified bi-level Breadth-First Search in the proposed trees to discover a high-performance architecture.
Multi-Scale Aligned Distillation for Low-Resolution Detection
However, this option traditionally hurts the detection performance much.
ICM-3D: Instantiated Category Modeling for 3D Instance Segmentation
Separating 3D point clouds into individual instances is an important task for 3D vision.
Single-DARTS: Towards Stable Architecture Search
Differentiable architecture search (DARTS) marks a milestone in Neural Architecture Search (NAS), boasting simplicity and small search costs.
Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision
In particular, Panoptic FCN encodes each object instance or stuff category with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly.
Scale-aware Automatic Augmentation for Object Detection
We propose Scale-aware AutoAug to learn data augmentation policies for object detection.
Reinforcement Learning for the Beginning of Starcraft II Game
In this project, we plan to develop a reinforcement learning model for the beginning of Starcraft II game, instead of the full-length game.
Joint COCO and Mapillary Workshop at ICCV 2019: COCO Instance Segmentation Challenge Track
In this report, we present our object detection/instance segmentation system, MegDetV2, which works in a two-pass fashion, first to detect instances then to obtain segmentation.
Dynamic Scale Training for Object Detection
We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection.
Learning Dynamic Routing for Semantic Segmentation
To demonstrate the superiority of the dynamic property, we compare with several static architectures, which can be modeled as special cases in the routing space.
PointINS: Point-based Instance Segmentation
In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features.
RENAS: Reinforced Evolutionary Neural Architecture Search
This architecture achieves a competitive result on CIFAR-10.
DetNAS: Backbone Search for Object Detection
In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection.
EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search
In our implementations, architectures are first searched on a small dataset, e. g., CIFAR-10.
Joint Neural Architecture Search and Quantization
Here our goal is to automatically find a compact neural network model with high performance that is suitable for mobile devices.
Reinforced Evolutionary Neural Architecture Search
To address this issue, we propose the Reinforced Evolutionary Neural Architecture Search (RE- NAS), which is an evolutionary method with the reinforced mutation for NAS.
