UIFormer: A Unified Transformer-based Framework for Incremental Few-Shot Object Detection and Instance Segmentation
This addresses the problem of learning new object classes with limited data while preserving old knowledge for computer vision applications, representing an incremental improvement over existing approaches.
The paper tackles incremental few-shot object detection and instance segmentation by extending Mask-DINO into a two-stage framework with classifier selection and knowledge distillation, achieving significant performance gains over state-of-the-art methods on COCO and LVIS datasets.
This paper introduces a novel framework for unified incremental few-shot object detection (iFSOD) and instance segmentation (iFSIS) using the Transformer architecture. Our goal is to create an optimal solution for situations where only a few examples of novel object classes are available, with no access to training data for base or old classes, while maintaining high performance across both base and novel classes. To achieve this, We extend Mask-DINO into a two-stage incremental learning framework. Stage 1 focuses on optimizing the model using the base dataset, while Stage 2 involves fine-tuning the model on novel classes. Besides, we incorporate a classifier selection strategy that assigns appropriate classifiers to the encoder and decoder according to their distinct functions. Empirical evidence indicates that this approach effectively mitigates the over-fitting on novel classes learning. Furthermore, we implement knowledge distillation to prevent catastrophic forgetting of base classes. Comprehensive evaluations on the COCO and LVIS datasets for both iFSIS and iFSOD tasks demonstrate that our method significantly outperforms state-of-the-art approaches.