Unveiling the Unknown: Conditional Evidence Decoupling for Unknown Rejection
- URL: http://arxiv.org/abs/2406.18443v1
- Date: Wed, 26 Jun 2024 15:48:24 GMT
- Title: Unveiling the Unknown: Conditional Evidence Decoupling for Unknown Rejection
- Authors: Zhaowei Wu, Binyi Su, Hua Zhang, Zhong Zhou,
- Abstract summary: We focus on training an open-set object detector under the condition of scarce training samples.
Under this challenging scenario, the decision boundaries of unknowns are difficult to learn and often ambiguous.
We develop a novel open-set object detection framework, which delves into conditional evidence decoupling for the unknown rejection.
- Score: 8.78242987271299
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this paper, we focus on training an open-set object detector under the condition of scarce training samples, which should distinguish the known and unknown categories. Under this challenging scenario, the decision boundaries of unknowns are difficult to learn and often ambiguous. To mitigate this issue, we develop a novel open-set object detection framework, which delves into conditional evidence decoupling for the unknown rejection. Specifically, we select pseudo-unknown samples by leveraging the discrepancy in attribution gradients between known and unknown classes, alleviating the inadequate unknown distribution coverage of training data. Subsequently, we propose a Conditional Evidence Decoupling Loss (CEDL) based on Evidential Deep Learning (EDL) theory, which decouples known and unknown properties in pseudo-unknown samples to learn distinct knowledge, enhancing separability between knowns and unknowns. Additionally, we propose an Abnormality Calibration Loss (ACL), which serves as a regularization term to adjust the output probability distribution, establishing robust decision boundaries for the unknown rejection. Our method has achieved the superiority performance over previous state-of-the-art approaches, improving the mean recall of unknown class by 7.24% across all shots in VOC10-5-5 dataset settings and 1.38% in VOC-COCO dataset settings. The code is available via https://github.com/zjzwzw/CED-FOOD.
Related papers
- Entropic Open-set Active Learning [30.91182106918793]
Active Learning (AL) aims to enhance the performance of deep models by selecting the most informative samples for annotation from a pool of unlabeled data.
Despite impressive performance in closed-set settings, most AL methods fail in real-world scenarios where the unlabeled data contains unknown categories.
We propose an Entropic Open-set AL framework which leverages both known and unknown distributions effectively to select informative samples during AL rounds.
arXiv Detail & Related papers (2023-12-21T18:47:12Z) - Open Set Relation Extraction via Unknown-Aware Training [72.10462476890784]
We propose an unknown-aware training method, regularizing the model by dynamically synthesizing negative instances.
Inspired by text adversarial attacks, we adaptively apply small but critical perturbations to original training instances.
Experimental results show that this method achieves SOTA unknown relation detection without compromising the classification of known relations.
arXiv Detail & Related papers (2023-06-08T05:45:25Z) - Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown
Objects [21.426594215463105]
We propose the unknown sniffer (UnSniffer) to find both unknown and known objects.
GOC score is introduced, which only uses known samples for supervision and avoids improper suppression of unknowns in the background.
We present the Unknown Object Detection Benchmark, the first publicly benchmark that encompasses precision evaluation for unknown detection to our knowledge.
arXiv Detail & Related papers (2023-03-24T02:59:44Z) - Adaptive Negative Evidential Deep Learning for Open-set Semi-supervised Learning [69.81438976273866]
Open-set semi-supervised learning (Open-set SSL) considers a more practical scenario, where unlabeled data and test data contain new categories (outliers) not observed in labeled data (inliers)
We introduce evidential deep learning (EDL) as an outlier detector to quantify different types of uncertainty, and design different uncertainty metrics for self-training and inference.
We propose a novel adaptive negative optimization strategy, making EDL more tailored to the unlabeled dataset containing both inliers and outliers.
arXiv Detail & Related papers (2023-03-21T09:07:15Z) - What is Flagged in Uncertainty Quantification? Latent Density Models for
Uncertainty Categorization [68.15353480798244]
Uncertainty Quantification (UQ) is essential for creating trustworthy machine learning models.
Recent years have seen a steep rise in UQ methods that can flag suspicious examples.
We propose a framework for categorizing uncertain examples flagged by UQ methods in classification tasks.
arXiv Detail & Related papers (2022-07-11T19:47:00Z) - Synthetic Unknown Class Learning for Learning Unknowns [0.0]
This paper proposes a novel synthetic unknown class learning method.
It generates unknown-like samples while maintaining diversity between the generated samples and learns these samples.
Experiments on several benchmark datasets show that the proposed method significantly outperforms other state-of-the-art approaches.
arXiv Detail & Related papers (2021-11-15T19:46:41Z) - Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object
Detection [66.10057490293981]
We propose a data-uncertainty guided multi-phase learning method for semi-supervised object detection.
Our method behaves extraordinarily compared to baseline approaches and outperforms them by a large margin.
arXiv Detail & Related papers (2021-03-29T09:27:23Z) - Learning Open Set Network with Discriminative Reciprocal Points [70.28322390023546]
Open set recognition aims to simultaneously classify samples from predefined classes and identify the rest as 'unknown'
In this paper, we propose a new concept, Reciprocal Point, which is the potential representation of the extra-class space corresponding to each known category.
Based on the bounded space constructed by reciprocal points, the risk of unknown is reduced through multi-category interaction.
arXiv Detail & Related papers (2020-10-31T03:20:31Z) - 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) - Conditional Gaussian Distribution Learning for Open Set Recognition [10.90687687505665]
We propose Conditional Gaussian Distribution Learning (CGDL) for open set recognition.
In addition to detecting unknown samples, this method can also classify known samples by forcing different latent features to approximate different Gaussian models.
Experiments on several standard image reveal that the proposed method significantly outperforms the baseline method and achieves new state-of-the-art results.
arXiv Detail & Related papers (2020-03-19T14:32:08Z)
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.