Partition, Refine, and Detect: Preserving Novel Category Capacity in Open-Vocabulary Object Detection
cs.CV, cs.LG
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
- Microsoft COCO Captions: Data Collection and Evaluation Server
- TALON: Test-time Adaptive Learning for On-the-Fly Category Discovery
- GPT-4 Technical Report
- Representation Learning with Contrastive Predictive Coding
- Qwen-Image Technical Report
- The Llama 3 Herd of Models
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