# Object-conditioned Bag of Instances for Few-Shot Personalized Instance Recognition

arXiv: https://arxiv.org/abs/2404.01397 · HTML: https://mlsanity.com/paper/2404.01397/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 1 Apr 2024.

## Builds on (most cited first, 13 of 13)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning](https://mlsanity.com/paper/1911.04623/) (2019)
- [Incremental Learning Techniques for Semantic Segmentation](https://mlsanity.com/paper/1907.13372/) (2019)
- [Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations](https://mlsanity.com/paper/2103.06342/) (2021)
- [Neural Collapse: A Review on Modelling Principles and Generalization](https://mlsanity.com/paper/2206.04041/) (2022)
- [Online Continual Learning for Robust Indoor Object Recognition](https://mlsanity.com/paper/2307.09827/) (2023)
- [Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics](https://mlsanity.com/paper/2307.12660/) (2023)
- [Few-shot Metric Learning: Online Adaptation of Embedding for Retrieval](https://mlsanity.com/paper/2211.07116/) (2022)
- [Are we done with object recognition? The iCub robot's perspective](https://mlsanity.com/paper/1709.09882/) (2017)
- [Few-shot Classification via Ensemble Learning with Multi-Order Statistics](https://mlsanity.com/paper/2305.00454/) (2023)
- [HOP to the Next Tasks and Domains for Continual Learning in NLP](https://mlsanity.com/paper/2402.18449/) (2024)

## Built on by (most cited first, 2 of 2)

- [MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment](https://mlsanity.com/paper/2509.14001/) (2025)
- [Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2501.15998/) (2025)

## Abstract (arXiv)

Nowadays, users demand for increased personalization of vision systems to localize and identify personal instances of objects (e.g., my dog rather than dog) from a few-shot dataset only. Despite outstanding results of deep networks on classical label-abundant benchmarks (e.g., those of the latest YOLOv8 model for standard object detection), they struggle to maintain within-class variability to represent different instances rather than object categories only. We construct an Object-conditioned Bag of Instances (OBoI) based on multi-order statistics of extracted features, where generic object detection models are extended to search and identify personal instances from the OBoI's metric space, without need for backpropagation. By relying on multi-order statistics, OBoI achieves consistent superior accuracy in distinguishing different instances. In the results, we achieve 77.1% personal object recognition accuracy in case of 18 personal instances, showing about 12% relative gain over the state of the art.