Open-Set Recognition Using Intra-Class Splitting

Schlachter, Patrick; Liao, Yi-Wen; Yang, Bin

doi:10.23919/eusipco.2019.8902738

Cited by 31 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intra-class Splitting Intra-class splitting (ICS) is a strategy to model unknown classes [30,31]. More precisely, given training samples are split into typical and atypical subsets.…”

Section: Threshold-based Open Set Recognizersmentioning

confidence: 99%

“…Thereby, the goal of the scoring procedure is to find those samples which are either incorrectly classified or correctly classified but with a low confidence. As a result, shows how many samples from known classes are allowed to be incorrectly rejected as unknown classes, similar to [31].…”

Section: Dynamic Intra-class Splitting (Dics)mentioning

confidence: 99%

“…The backbone neural network architecture of the DICS method shared the same settings with [31]. The batch size…”

Section: Setupmentioning

confidence: 99%

See 2 more Smart Citations

Deep Open Set Recognition Using Dynamic Intra-class Splitting

2020

Self Cite

View full text Add to dashboard Cite

This paper provides a generic deep learning method to solve open set recognition problems. In open set recognition, only samples of a limited number of known classes are given for training. During inference, an open set recognizer must not only correctly classify samples from known classes, but also reject samples from unknown classes. Due to these specific requirements, conventional deep learning models that assume a closed set environment cannot be used. Therefore, special open set approaches were taken, including variants of support vector machines and generation-based state-of-the-art methods which model unknown classes by generated samples. In contrast, our proposed method models unknown classes by atypical subsets of training samples. The subsets are obtained through intra-class splitting (ICS). Based on a recently proposed two-stage algorithm using ICS, we propose a one-stage method based on alternating between ICS and the training of a deep neural network. Finally, several experiments were conducted to compare our proposed method with conventional and other state-of-the-art methods. The proposed method based on dynamic ICS showed a comparable or better performance than all considered existing methods regarding balanced accuracy.

show abstract

“…Intra-class Splitting Intra-class splitting (ICS) is a strategy to model unknown classes [30,31]. More precisely, given training samples are split into typical and atypical subsets.…”

Section: Threshold-based Open Set Recognizersmentioning

confidence: 99%

Section: Dynamic Intra-class Splitting (Dics)mentioning

confidence: 99%

See 1 more Smart Citation

Deep Open Set Recognition Using Dynamic Intra-class Splitting

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Open set problem [33] assumes testing samples can come from classes invisible during training. Current open set recognition literature either re-estimate the class probabilities [1,34,18] so that it can be more sensitive to negative classes, or uses generative methods [11,24] to synthesize fake images that can be used for training additional negative class. Different from the above methods, we model the negative class from prototype envisioning to improve the few-shot open-set robustness.…”

Section: Related Workmentioning

confidence: 99%

“…The system is trained to distinguish the predefined classes as well as detect/reject queries from negative classes (negative queries). Recent works either proposes new probability estimation methods [1,34] to make the classifier more sensitive to outliers, or use generative methods [11,24] to create synthetic images using GAN [14,22] to represent negative classes (Figure 1(a)). However, they rely on sufficient labeled training data to learn good class distributions for effective classification and rejection.…”

Section: Introductionmentioning

confidence: 99%

Task-Adaptive Negative Envision for Few-Shot Open-Set Recognition

Huang¹,

Ma²,

Han³

et al. 2020

Preprint

View full text Add to dashboard Cite

Recent works seek to endow recognition systems with the ability to handle the open world. Few shot learning aims for fast learning of new classes from limited examples, while open-set recognition considers unknown negative class from the open world. In this paper, we study the problem of few-shot open-set recognition (FSOR), which learns a recognition system robust to queries from new sources with few examples and from unknown open sources. To achieve that, we mimic human capability of envisioning new concepts from prior knowledge, and propose a novel task-adaptive negative class envision method (TANE) to model the open world. Essentially we use an external memory to estimate a negative class representation. Moreover, we introduce a novel conjugate episode training strategy that strengthens the learning process. Extensive experiments on four public benchmarks show that our approach significantly improves the state-of-the-art performance on few-shot open-set recognition. Besides, we extend our method to generalized few-shot open-set recognition (GFSOR), where we also achieve performance gains on MiniImageNet.

show abstract