Losing the name before the box: measuring and repairing what narrow fine-tuning costs a detector outside its deployment vocabulary
cs.RO, cs.CV, cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Comments: 25 pages, 3 figures. Supplementary material (69 pages) is included as an ancillary file. Submitted to the International Journal of Computer Vision
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Not All Forgetting Is Equal: Retention Dynamics in Fine-Tuned Image Classifiers
- YOLOX: Exceeding YOLO Series in 2021
- Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives
- Extending One-Stage Detection with Open-World Proposals
- Mitigating Objectness Bias and Region-to-Text Misalignment for Open-Vocabulary Panoptic Segmentation
- Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift
- Textual Inversion for Efficient Adaptation of Open-Vocabulary Object Detectors Without Forgetting
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies