# Class-Incremental Few-Shot Object Detection Source: [Class-Incremental Few-Shot Object Detection]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:50:06.694Z Authors: Pengyang Li, Yanan Li, Han Cui, Donghui Wang Published: 2021-05-17T06:49:29.000Z ## Abstract Conventional detection networks usually need abundant labeled training samples, while humans can learn new concepts incrementally with just a few examples. This paper focuses on a more challenging but realistic class-incremental few-shot object detection problem (iFSD). It aims to incrementally transfer the model for novel objects from only a few annotated samples without catastrophically forgetting the previously learned ones. To tackle this problem, we propose a novel method LEAST, which can transfer with Less forgetting, fEwer training resources, And Stronger Transfer capability. Specifically, we first present the transfer strategy to reduce unnecessary weight adaptation and improve the transfer capability for iFSD. On this basis, we then integrate the knowledge distillation technique using a less resource-consuming approach to alleviate forgetting and propose a novel clustering-based exemplar selection process to preserve more discriminative features previously learned. Being a generic and effective method, LEAST can largely improve the iFSD performance on various benchmarks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on COCO (AP by Class Type)](): Object Detection; COCO; AP (New classes): 12.5. ## Original sources and implementation [Original paper]() [PDF]()