# Incrementally Zero-Shot Detection by an Extreme Value Analyzer

arXiv: https://arxiv.org/abs/2103.12609 · HTML: https://mlsanity.com/paper/2103.12609/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 42 references that are in the map.
- First posted on arXiv 23 Mar 2021.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Zero-Shot Learning -- The Good, the Bad and the Ugly](https://mlsanity.com/paper/1703.04394/) (2017)
- [Incremental Learning of Object Detectors without Catastrophic Forgetting](https://mlsanity.com/paper/1708.06977/) (2017)
- [Zero-Shot Object Detection](https://mlsanity.com/paper/1804.04340/) (2018)
- [An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild](https://mlsanity.com/paper/1605.04253/) (2016)
- [Semantic Autoencoder for Zero-Shot Learning](https://mlsanity.com/paper/1704.08345/) (2017)
- [Latent Embeddings for Zero-shot Classification](https://mlsanity.com/paper/1603.08895/) (2016)
- [The Extreme Value Machine](https://mlsanity.com/paper/1506.06112/) (2015)
- [Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions](https://mlsanity.com/paper/1506.00511/) (2015)
- [Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts](https://mlsanity.com/paper/1803.06049/) (2018)
- [Zero-Shot Learning via Joint Latent Similarity Embedding](https://mlsanity.com/paper/1511.04512/) (2015)
- [Zero-Shot Object Detection by Hybrid Region Embedding](https://mlsanity.com/paper/1805.06157/) (2018)
- [Recent Advances in Zero-shot Recognition](https://mlsanity.com/paper/1710.04837/) (2017)
- [Zero-Shot Detection](https://mlsanity.com/paper/1803.07113/) (2018)
- [Polarity Loss for Zero-shot Object Detection](https://mlsanity.com/paper/1811.08982/) (2018)
- [Extreme Value Theory for Open Set Classification -- GPD and GEV Classifiers](https://mlsanity.com/paper/1808.09902/) (2018)

## Built on by (most cited first, 1 of 1)

- [A Survey of Deep Learning for Low-Shot Object Detection](https://mlsanity.com/paper/2112.02814/) (2021)

## Abstract (arXiv)

Human beings not only have the ability to recognize novel unseen classes, but also can incrementally incorporate the new classes to existing knowledge preserved. However, zero-shot learning models assume that all seen classes should be known beforehand, while incremental learning models cannot recognize unseen classes. This paper introduces a novel and challenging task of Incrementally Zero-Shot Detection (IZSD), a practical strategy for both zero-shot learning and class-incremental learning in real-world object detection. An innovative end-to-end model -- IZSD-EVer was proposed to tackle this task that requires incrementally detecting new classes and detecting the classes that have never been seen. Specifically, we propose a novel extreme value analyzer to detect objects from old seen, new seen, and unseen classes, simultaneously. Additionally and technically, we propose two innovative losses, i.e., background-foreground mean squared error loss alleviating the extreme imbalance of the background and foreground of images, and projection distance loss aligning the visual space and semantic spaces of old seen classes. Experiments demonstrate the efficacy of our model in detecting objects from both the seen and unseen classes, outperforming the alternative models on Pascal VOC and MSCOCO datasets.