Multi-Attribute Open Set Recognition
- URL: http://arxiv.org/abs/2208.06809v1
- Date: Sun, 14 Aug 2022 09:04:52 GMT
- Title: Multi-Attribute Open Set Recognition
- Authors: Piyapat Saranrittichai, Chaithanya Kumar Mummadi, Claudia Blaiotta,
Mauricio Munoz and Volker Fischer
- Abstract summary: We introduce a novel problem setup that generalizes conventional OSR to a multi-attribute setting.
We show that these baselines are vulnerable to shortcuts when spurious correlations exist in the training dataset.
We provide an empirical evidence showing that this behavior is consistent across different baselines on both synthetic and real world datasets.
- Score: 7.012240324005977
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Open Set Recognition (OSR) extends image classification to an open-world
setting, by simultaneously classifying known classes and identifying unknown
ones. While conventional OSR approaches can detect Out-of-Distribution (OOD)
samples, they cannot provide explanations indicating which underlying visual
attribute(s) (e.g., shape, color or background) cause a specific sample to be
unknown. In this work, we introduce a novel problem setup that generalizes
conventional OSR to a multi-attribute setting, where multiple visual attributes
are simultaneously recognized. Here, OOD samples can be not only identified but
also categorized by their unknown attribute(s). We propose simple extensions of
common OSR baselines to handle this novel scenario. We show that these
baselines are vulnerable to shortcuts when spurious correlations exist in the
training dataset. This leads to poor OOD performance which, according to our
experiments, is mainly due to unintended cross-attribute correlations of the
predicted confidence scores. We provide an empirical evidence showing that this
behavior is consistent across different baselines on both synthetic and real
world datasets.
Related papers
- Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection [71.93411099797308]
Out-of-distribution (OOD) samples are crucial when deploying machine learning models in open-world scenarios.
We propose to tackle this constraint by leveraging the expert knowledge and reasoning capability of large language models (LLM) to potential Outlier Exposure, termed EOE.
EOE can be generalized to different tasks, including far, near, and fine-language OOD detection.
EOE achieves state-of-the-art performance across different OOD tasks and can be effectively scaled to the ImageNet-1K dataset.
arXiv Detail & Related papers (2024-06-02T17:09:48Z) - CREST: Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot Learning [48.46511584490582]
Zero-shot learning (ZSL) enables the recognition of novel classes by leveraging semantic knowledge transfer from known to unknown categories.
Real-world challenges such as distribution imbalances and attribute co-occurrence hinder the discernment of local variances in images.
We propose a bidirectional cross-modal ZSL approach CREST to overcome these challenges.
arXiv Detail & Related papers (2024-04-15T10:19:39Z) - Exploring Diverse Representations for Open Set Recognition [51.39557024591446]
Open set recognition (OSR) requires the model to classify samples that belong to closed sets while rejecting unknown samples during test.
Currently, generative models often perform better than discriminative models in OSR.
We propose a new model, namely Multi-Expert Diverse Attention Fusion (MEDAF), that learns diverse representations in a discriminative way.
arXiv Detail & Related papers (2024-01-12T11:40:22Z) - A Survey on Open-Set Image Recognition [18.474539379698538]
Open-set image recognition (OSR) aims to both classify known-class samples and identify unknown-class samples in the testing set.
We introduce a new taxonomy, under which we comprehensively review the existing DNN-based OSR methods.
We compare the performances of some typical and state-of-the-art OSR methods on both coarse-grained datasets and fine-grained datasets.
arXiv Detail & Related papers (2023-12-25T00:30:23Z) - LORD: Leveraging Open-Set Recognition with Unknown Data [10.200937444995944]
LORD is a framework to Leverage Open-set Recognition by exploiting unknown data.
We identify three model-agnostic training strategies that exploit background data and applied them to well-established classifiers.
arXiv Detail & Related papers (2023-08-24T06:12:41Z) - A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual
Information Minimization for Pedestrian Attribute Recognition [10.821982414387525]
We show that current methods can actually suffer in generalizing such fitted attributes interdependencies onto scenes or identities off the dataset distribution.
To render models robust in realistic scenes, we propose the attributes-disentangled feature learning to ensure the recognition of an attribute not inferring on the existence of others.
arXiv Detail & Related papers (2023-07-28T01:34:55Z) - The Devil is in the Wrongly-classified Samples: Towards Unified Open-set
Recognition [61.28722817272917]
Open-set Recognition (OSR) aims to identify test samples whose classes are not seen during the training process.
Recently, Unified Open-set Recognition (UOSR) has been proposed to reject not only unknown samples but also known but wrongly classified samples.
arXiv Detail & Related papers (2023-02-08T11:34:04Z) - Class-Specific Semantic Reconstruction for Open Set Recognition [101.24781422480406]
Open set recognition enables deep neural networks (DNNs) to identify samples of unknown classes.
We propose a novel method, called Class-Specific Semantic Reconstruction (CSSR), that integrates the power of auto-encoder (AE) and prototype learning.
Results of experiments conducted on multiple datasets show that the proposed method achieves outstanding performance in both close and open set recognition.
arXiv Detail & Related papers (2022-07-05T16:25:34Z) - Open Set Recognition with Conditional Probabilistic Generative Models [51.40872765917125]
We propose Conditional Probabilistic Generative Models (CPGM) for open set recognition.
CPGM can detect unknown samples but also classify known classes by forcing different latent features to approximate conditional Gaussian distributions.
Experiment results on multiple benchmark datasets reveal that the proposed method significantly outperforms the baselines.
arXiv Detail & Related papers (2020-08-12T06:23:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.