Fear of Memorizing Objects: End-to-End Zero-Shot Model-Based Object Detection
cs.CV
Submitted: 2026-11-11
Updated: 2026-11-11
Code: https://github.com/swtyree/hope-dataset
Project page: https://nvlabs.github.io/HANDAL/10
Terminology
Sources
- Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking
- MUSE: Model-based Uncertainty-aware Similarity Estimation for zero-shot 2D Object Detection and Segmentation
- NOCTIS: Novel Object Cyclic Threshold based Instance Segmentation
- Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
- MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare
- Decoupled Weight Decay Regularization
- Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation
- Accelerating 3D Deep Learning with PyTorch3D
- Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
- Harmonizing de Broglie-Bohm's Causal Interpretation with the Copenhagen Interpretation of Quantum Mechanics
- PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
- Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation
- Deformable DETR: Deformable Transformers for End-to-End Object Detection
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs