Method that adapts expectation-maximization (EM) to aggregate annotations that work on tasks with combined localization and classification like object detection and instance segmentation.

A method that randomly mask out (replaces with some numerical value, usually zero) all features coming from a specific band in multi-spectral data.

Band Dropout

Lightweight, Pre-trained Transformers for Remote Sensing Timeseries

LAEM

Drawing the Same Bounding Box Twice? Coping Noisy Annotations in Object Detection with Repeated Labels

A method that can recover the weights of the pre-fine-tuning model using a few low-rank (LoRA) fine-tuned models. In contrast to previous attacks that attempt to recover pre-fine-tuning capabilities, Spectral DeTuning aims to recover the exact pre-fine-tuning *weights*. Spectral DeTuning can exploit this vulnerability against large-scale models such as a personalized Stable Diffusion and an aligned Mistral.

Source	Drawing the Same Bounding Box Twice? Coping Noisy Annotations in Object Detection with Repeated Labels
Year
Data Source	Papers with Code archive (CC BY-SA)