No article text was recorded for this version.
synthetic occlusion augmentation (occlusion-robust feature learning)
Version 1 of 174 papers85 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Diverse Learner: Exploring Diverse Supervision for Semi-supervised Object Detection
- Blog: GraspClutter6D: A Large-scale Real-world Dataset for Robust Perception and Grasping in Cluttered Scenes
- Blog: Occlusion-Robust Object Pose Estimation with Holistic Representation
- Blog: Learning from synthetic data generated with GRADE
- Blog: Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving
- Blog: Multi-branch Siamese Network for High Performance Online Visual Tracking
- Blog: An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation
- Blog: SIDOD: A Synthetic Image Dataset for 3D Object Pose Recognition With Distractors
- Blog: Survey: Image mixing and deleting for data augmentation
- Blog: End-to-End Differentiable 6DoF Object Pose Estimation with Local and Global Constraints
- Blog: Are Local Features All You Need for Cross-Domain Visual Place Recognition?
- Blog: PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes
- Blog: Recognition of Cheating Behaviors Based on Finetuning of Model Parameters
- Blog: Face Attention Network: An Effective Face Detector for the Occluded Faces
- Blog: Using Images Rendered by PBRT to Train Faster R-CNN for UAV Detection
- Blog: SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud
- Blog: EventDrop: Data Augmentation for Event-based Learning
- Blog: Person re-identification with effectively designed parts
- Blog: Evaluation of post-hoc interpretability methods in time-series classification
- Blog: Feel the Bite: Robot-Assisted Inside-Mouth Bite Transfer using Robust Mouth Perception and Physical Interaction-Aware Control
- Blog: SUMix: Mixup with Semantic and Uncertain Information
- Blog: Bridging between Computer and Robot Vision through Data Augmentation: a Case Study on Object Recognition
- Blog: SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation
- Blog: PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition
- Blog: Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters
- Blog: Context-Aware Data Augmentation for LIDAR 3d Object Detection
- Blog: SemiETPicker: Fast and Label-Efficient Particle Picking for CryoET Tomography Using Semi-Supervised Learning
- Blog: Adversarial Semantic Data Augmentation for Human Pose Estimation
- Blog: Deep feature augmentation for occluded image classification
- Blog: A Cascade Defense Method for Multidomain Adversarial Attacks under Remote Sensing Detection
- Blog: When Face Recognition Meets Occlusion: A New Benchmark
- Blog: Learning Landmark Guided Embeddings for Animal Re-identification
- Blog: AdvMask: A sparse adversarial attack-based data augmentation method for image classification
- Blog: PMPred-AE: a computational model for the detection and interpretation of pathological myopia based on artificial intelligence
- Blog: TdAttenMix: Top-Down Attention Guided Mixup
- Blog: Removing Backdoor-Based Watermarks in Neural Networks with Limited Data
- Blog: Masked Face Recognition Challenge: The InsightFace Track Report
- Blog: Generating Features with Increased Crop-Related Diversity for Few-Shot Object Detection
- Blog: A Hybrid Excitation Model Based Lightweight Siamese Network for Underwater Vehicle Object Tracking Missions
- Blog: WALDO: Where Unseen Model-based 6D Pose Estimation Meets Occlusion
- Blog: Kernelized Memory Network for Video Object Segmentation
- Blog: Multiple Object Tracking as ID Prediction
- Blog: ShapeAug++: More Realistic Shape Augmentation for Event Data
- Blog: PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes
- Blog: Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring
- Blog: CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes
- Blog: Unlocking the Potential of Data Augmentation in Contrastive Learning for Hyperspectral Image Classification
- Blog: Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding
- Blog: Dual-Channel Autoencoder with Key Region Feature Enhancement for Video Anomalous Event Detection
- Blog: Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models
- Blog: Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring
- Blog: Generative Adversarial Training for Weakly Supervised Cloud Matting
- Blog: Part Segmentation for Highly Accurate Deformable Tracking in Occlusions via Fully Convolutional Neural Networks
- Blog: Soft Augmentation for Image Classification
- Blog: MagnifierNet: Towards Semantic Adversary and Fusion for Person Re-identification
- Blog: Improved YOLOv5-based for small traffic sign detection under complex weather
- Blog: Understanding Masked Image Modeling via Learning Occlusion Invariant Feature
- Blog: Generalizable Pedestrian Detection: The Elephant in the Room
- Blog: Multi-Scale Structure-Aware Network for Human Pose Estimation
- Blog: Cascade Transformers for End-to-End Person Search
Showing 60 of 74 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_synthetic_occlusion_augmentation_occlusi_cf522d96,
title = {synthetic occlusion augmentation (occlusion-robust feature learning)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/synthetic-occlusion-augmentation-occlusion-robust-feature-learning/rdr_cf522d96ef504c8090a1515fa083191f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_synthetic_occlusion_augmentation_occlusi_cf522d96_v1,
title = {synthetic occlusion augmentation (occlusion-robust feature learning)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/synthetic-occlusion-augmentation-occlusion-robust-feature-learning/rdr_cf522d96ef504c8090a1515fa083191f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}