Reading Collections
Others
2D Object Detection
AP-Loss for Accurate One-Stage Object Detection
Associative Embedding
BoF for object detection (tricks)
Cornet Proposal Network
CenterNet
CornetNet-Lite
CornetNet
Distance-IoU Loss
Dynamic Refinement Network
Dynamic RCNN
EfficientDet
FCOS, anchorless one-stage object detection
Generalized Focal Loss
Gaussian YOLOv3
IoU-uniform R-CNN
IoU Net(s) - A summary
Some Collections around MMDetection
Exploiting Event Cameras by Using a Network Grafting Algorithm
Detection and Tracking as Point
Probabilistic Anchor Assignment with IoU Prediction for Object Detection
Recurrent Vision Transformers for Object Detection with Event Cameras
The RepPoints Series
SSD
ThunderNet
YOLOv4
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection
Anchor DETR
Balance-Oriented Focal Loss with Linear Scheduling for Anchor Free Object Detection
Deformable DETR
DE⫶TR
Implicit Feature Pyramid Network for Object Detection
OneNet: Towards End-to-End One-Stage Object Detection
PIX2SEQ: A Language Modeling Framework for Object Detection
PolarNet
Slender Object Detection: Diagnoses and Improvements
Towards Open World Object Detection
Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectors
You Only Look One-level Feature
YOLOX: Exceeding YOLO Series in 2021
Deep Navigation
ChauffeurNet
Drifting with RL (Cai, Mei)
DroNet
Domain Transfer Imitation - Tai Lei
Gaze Training - Chen Yuying
ModEL: A Modularized End-to-end Reinforcement Learning Framework for Autonomous Driving
Task-Aware Generative Uncertainty
Segmentation
Actor-Critic Instance Segmentation
Summary of Multiple Papers on BEV Fusion
Convolutional CRF
Deep Multi-Sensor Lane Detection
Deep Snake
Fully Convolutional Networks for Panoptic Segmentation (Panoptic FCN)
LRNNet
Cascade Lane Detection
PointRend
PolarMask
RDSNet
SAUNet
SOLO for instance Seg
Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction
TensorMask-Instance Seg
Ultra Fast Structure-aware Deep Lane Detection
YOLOACT
BlendMask
Conditional Convolutions for Instance Segmentation
Focus on Local: Detecting Lane Marker from Bottom Up via Key Point
FreeSOLO
HDMapNet: An Online HD Map Construction and Evaluation Framework
Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D
MMSegmentation
Hierarchical Multi-scale Attention for Semantic Segmentation
OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception
PanopticBEV
PyrOccNet for BEV Segmentation
SkyEye: Self-Supervised Bird’s-Eye-View Semantic Mapping Using Monocular Frontal View Images
UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering
SLAM
Interval-Based Visual-LiDAR Sensor Fusion
BAD SLAM: Bundle Adjusted Direct RGB-D SLAM
CubeSLAM
DISK: Learning local features with policy gradient
DeepICP
UnDepthFlow
LO-Net
PWC-Net
SuperPoint
Unsupervised Learning of Depth and Ego-Motion from Video
VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residuals
Summaries
Collections of Stereo Matching from KITTI
Robotics_DL Lecture from georgia Tech
Self-Attention & CNN
Summary of Mono 3D Detection in 2019
Summary of Single Stage Instance Segmentation
Summary of Temperal BEV
CVPR 2021 clips
ICCV 2021 clips
ICLR 2021 clips
ICML 2021 clips
Summary of Several Map Extraction Papers
Summary of NIPS 2020 for application
NeurIPS 2021 clips
ICRA 2020 clips
Segmentation Loss Odyssey
CVPR 2020 clips
ECCV 2020 clips
ICCV 2019 Clips
Depth Completion & Depth Prediction
DNet for Depth Prediction
Deep Line Encoding for Monocular 3D Object Detection and Depth Prediction
Deterministic Guided LiDAR Depth Map Completion
Soft Labels for Ordinal Regression
LiDAR completion with RGB uncertainty
Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR
Depth Prediction before DL
DORN Depth Prediction
GuideNet
On the Sins of Image Synthesis Loss for Self-supervised Depth Estimation
ManyDepth
MonoUncertainty
MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera
Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learning
Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks
Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction
Learning Steering Kernels for Guided Depth Completion
SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimation
When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation
Variational Monocular Depth Estimation for Reliability Prediction
Others
AcfNet
Attacking Optical Flow
CAM: Class Activation Map
Intensity Estimation With Event Cameras
FADNet
GPLVM
Gated2Depth
Gaussian Process and Variantional Autoencoder
Hyperparameter Tuning
Depth Completion on CPU
Joint Deraining and Dehazing
OptNet, Optimization as Layer
Image Reconstruction with Event Camera
PSMNet
PointFlow
R2D2
SPM - SPR
More on Differentiable Convex Optimization
Trust Region Policy Optimization
Unsupervised Mono Depth from stereo
Adversarial Patch
Detecting Twenty-thousand Classes using Image-level Supervision
FlowNet & More
Gaussian Splatting
Generative Modeling by Estimating Gradients of the Data Distribution
High-Performance Long-Term Tracking with Meta-Updater
MixMatch: A Holistic Approach to Semi-Supervised Learning
Collections on Monodepth (unsupervised)
MonoLayout
How can objects help action recognition?
OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression
OpenPose: Part Affinity Fields
PatchmatchNet: Learned Multi-View Patchmatch Stereo
Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning
SsSMnet
Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks
Plane sweeping for multi-image matching
About Surround Monodepth
TraDeS
VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation
ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
3dDetection
CenterNet for Point cloud
Color-Embedded 3D Reconstructio Mono3D
Wasserstein Distances for Stereo Disparity Estimation
camera distance-aware Mono 3D pose estimation
DSGN
MonoDIS
EGFN: Efficient Geometry Feature Network for Fast Stereo 3D Object Detection
End-to-end Learning of Multi-sensor 3D Tracking by Detection
FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
Fast and Furious
Frustum PointNets
Generalization for 3D Detection
Genearlized IoU 2D and 3D
Ground-aware Monocular 3D Object Detection for Autonomous Driving
From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection: (H23D-RCNN)
Multi-View Synthesis for Orientation Estimation
IoU Loss for 2D/3D Object Detection
Kinematic 3D Object Detection in Monocular Video
LaserNet
M3D-RPN
3D detection evaluation metric
Mono3d with virtual cameras
MonoGRNet
Single Shot Mono 3D(SS3D)
MV3D
OftNet
Pseudo-Lidar with Instance Segmentation
Recent Collections for Mono3D
Recent Collections for Stereo 3D
RefinedMPL
Shift RCNN
SSL-RTM3D
single-stage 3D Pose Estimation
TLNet
VoteNet & ImVoteNet
YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection
CaDDN
Digging Into Output Representation For Monocular 3D Object Detection
Is Pseudo-Lidar needed for Monocular 3D Object detection? (DD3D)
Monocular Differentiable Rendering for Self-Supervised 3D Object Detection
MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation
Multi-Sensor Refinement - Li Peiliang
Synthetic Cookbook for Using/Testing/Demonstrating VisualDet3D in ROS
Collections on PointNet and follow-ups
PVNet
Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection
RenderOcc
siaNMS
VoxelNet
Weakly Supervised 3D Object Detection from Point Clouds
Building Blocks
Minkowski Convolutional Neural Networks
Asymmetric Loss For Multi-Label Classification (ASL Loss)
AugMix
AdaIn Style Transfer
Attention Augmented Convolution
Self-Attention Mechanism
backprob through PnP Optimization
CBAM: Convolutional Block Attention Module
Deep GCN
Container: Context Aggregation Network
DGCNN and edgeConv
DO-Conv
DiCENet
keypointNet
Dynamic Conditional Networks for Few-Shot Learning
Dynamic Filtering Network
Elastic: Dynamic Scaling CNNs
EfficientNet
Ghost Net
Gumbel_softmax; Differentiable Indexing
HRNet
New Optimizers
MDEQ
MLP in Image Classification
Neural Relational Inference Model (NRI)
Non-local Neural Networks
On Multiplicative Integration with Recurrent Neural Networks
PointAtrousNet
Positional Normalization
RepVGG
SPN, CSPN and CSPN ++
SqueezeNet
Receptive Field Block
Squeeze-and-Excitation Networks
Stacked Hourglass Networks
A ConvNet for the 2020s (ConvNeXt)
Cross-iteration BatchNormalization
Deep Pruner & Differentiable Patch Match
Deformable ConvNet V2
FcaNet: Frequency Channel Attention Networks
Gabor Layers
Involution: Inverting the Inherence of Convolution for Visual Recognition
MonoViT
MutualNet
OMNIVORE: A Single Model for Many Visual Modalities
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
RepLKNet
Shape Adaptor
Swin Transformer V2: Scaling Up Capacity and Resolution
Planning Control DL
Model Predicvtive Path Integral Control
BackProp Kalman Filter
Cognitive Mapping and Planning
Composable Action-Conditioned Predictors
DESPOT-α
DAN for Composable Robot Learning
Differentiable MPC
EUDM Planning
Hierarchical Imitation and Reinforcement Learning
Intention-Net
LMPC_GP
PMPNet
Path Integral Networks
QMDP-Net
SUNRISE
Universal Planning Networks
differentiable pre-stablized MPC
End-to-end Autonomous Driving: Challenges and Frontiers
Theorotical DL
Covariance matrix adaptation evolution strategy: CMA-ES
Position Information in CNN
Channel Pruning for Accelerating Very Deep Neural Networks
Deconvolution and Checkerboard Artifacts
Train longer, generalize better: closing the generalization gap in large batch training of neural networks
Continuous Learning
Convex Optimization
Designing Network Design Spaces
Direct Loss Minimization
Do Better ImageNet Models Transfer Better?
First Order Optimizers
Uncertainty Propagation in Neural Network
FreeAnchor
LQF: Linear Quadratic Fine-Tuning
Localization-aware Channel Pruning
NIPS 2020 for Experimental NN
Neural Tangent Kernel: Convergence and Generalization in Neural Networks
Rethinking ImageNet Pre-training
ShuffleNet V2
Style and Normalization
Translation invariance in CNN
Understanding Deep Learning Requires Rethinking Generalization
Auto-Encoding Variational Bayes
VovNet
WHY GRADIENT CLIPPING ACCELERATES TRAINING: A THEORETICAL JUSTIFICATION FOR ADAPTIVITY
Bayesian Neural Network
Assembled Techniques for CNN
Deep Declarative Networks
Deep Learning "Foundations"
Denoising Diffusion Probabilistic Models
Emerging Properties in Self-Supervised Vision Transformers
An Introduction to Locally Linear Embedding
Mean Field Theory in Deep Learning
Mind The Pad - CNNs Can Develop Blind Spots
Momentum Batch Normalization
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
Visualizing the Loss Landscape of Neural Nets
Search
Previous
Next
MULTI-SCALE DENSE NETWORKS FOR RESOURCE EFFICIENT IMAGE CLASSIFICATION
MULTI-SCALE DENSE NETWORKS FOR RESOURCE EFFICIENT IMAGE CLASSIFICATION
Search
×
Close
From here you can search these documents. Enter your search terms below.
Keyboard Shortcuts
×
Close
Keys
Action
?
Open this help
n
Next page
p
Previous page
s
Search