# NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging

arXiv: https://arxiv.org/abs/2303.04958 · HTML: https://mlsanity.com/paper/2303.04958/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 9 Mar 2023.

## Builds on (most cited first, 28 of 28)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector](https://mlsanity.com/paper/1908.01998/) (2019)
- [Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning](https://mlsanity.com/paper/1909.13032/) (2019)
- [FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding](https://mlsanity.com/paper/2103.05950/) (2021)
- [Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild](https://mlsanity.com/paper/2007.12107/) (2020)
- [Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning](https://mlsanity.com/paper/2106.09701/) (2021)
- [Multi-Scale Positive Sample Refinement for Few-Shot Object Detection](https://mlsanity.com/paper/2007.09384/) (2020)
- [DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection](https://mlsanity.com/paper/2108.09017/) (2021)
- [Incremental Few-Shot Object Detection](https://mlsanity.com/paper/2003.04668/) (2020)
- [Generalized Few-Shot Object Detection without Forgetting](https://mlsanity.com/paper/2105.09491/) (2021)
- [Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection](https://mlsanity.com/paper/2103.04612/) (2021)
- [Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation](https://mlsanity.com/paper/2103.11731/) (2021)
- [Dual-Awareness Attention for Few-Shot Object Detection](https://mlsanity.com/paper/2102.12152/) (2021)
- [Lifelong Object Detection](https://mlsanity.com/paper/2009.01129/) (2020)
- [CFA: Constraint-based Finetuning Approach for Generalized Few-Shot Object Detection](https://mlsanity.com/paper/2204.05220/) (2022)

## Built on by (most cited first, 10 of 10)

- [Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector](https://mlsanity.com/paper/2402.03094/) (2024)
- [Detect Everything with Few Examples](https://mlsanity.com/paper/2309.12969/) (2023)
- [No time to train! Training-Free Reference-Based Instance Segmentation](https://mlsanity.com/paper/2507.02798/) (2025)
- [Multi-Perspective Data Augmentation for Few-shot Object Detection](https://mlsanity.com/paper/2502.18195/) (2025)
- [Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection](https://mlsanity.com/paper/2504.07060/) (2025)
- [BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairments](https://mlsanity.com/paper/2407.18243/) (2024)
- [FSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusion](https://mlsanity.com/paper/2602.03137/) (2026)
- [Few-Shot Pattern Detection via Template Matching and Regression](https://mlsanity.com/paper/2508.17636/) (2025)
- [Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection](https://mlsanity.com/paper/2606.23069/) (2026)
- [Few-Shot Object Detection via Spatial-Channel State Space Model](https://mlsanity.com/paper/2507.15308/) (2025)

## Abstract (arXiv)

Privacy and memory are two recurring themes in a broad conversation about the societal impact of AI. These concerns arise from the need for huge amounts of data to train deep neural networks. A promise of Generalized Few-shot Object Detection (G-FSOD), a learning paradigm in AI, is to alleviate the need for collecting abundant training samples of novel classes we wish to detect by leveraging prior knowledge from old classes (i.e., base classes). G-FSOD strives to learn these novel classes while alleviating catastrophic forgetting of the base classes. However, existing approaches assume that the base images are accessible, an assumption that does not hold when sharing and storing data is problematic. In this work, we propose the first data-free knowledge distillation (DFKD) approach for G-FSOD that leverages the statistics of the region of interest (RoI) features from the base model to forge instance-level features without accessing the base images. Our contribution is three-fold: (1) we design a standalone lightweight generator with (2) class-wise heads (3) to generate and replay diverse instance-level base features to the RoI head while finetuning on the novel data. This stands in contrast to standard DFKD approaches in image classification, which invert the entire network to generate base images. Moreover, we make careful design choices in the novel finetuning pipeline to regularize the model. We show that our approach can dramatically reduce the base memory requirements, all while setting a new standard for G-FSOD on the challenging MS-COCO and PASCAL-VOC benchmarks.