Sparse Representation-Based Open Set Recognition

By He Zhang, Vishal M. Patel. 2017

206 citations recorded by the source corpus.

We propose a generalized Sparse Representation-based Classification (SRC) algorithm for open set recognition where not all classes presented during testing are known during training. The SRC algorithm uses class reconstruction errors for classification. As most of the discriminative information for open set recognition is hidden in the tail part of the matched and sum of non-matched reconstruction error distributions, we model the tail of those two error distributions using the statistical Extreme Value Theory (EVT). Then we simplify the open set recognition problem into a set of hypothesis testing problems. The confidence scores corresponding to the tail distributions of a novel test sample are then fused to determine its identity. The effectiveness of the proposed method is demonstrated using four publicly available image and object classification datasets and it is shown that this method can perform significantly better than many competitive open set recognition algorithms.

Subfields: Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

The limits and potentials of deep learning for robotics (2018, background): “Preliminary work exploring this idea has included slab-based linear classiﬁers to limit the risk of half-spaces [102], nearest non-outlier models [11], and extreme value theory-based calibration of decision boundaries [12], [103], [135].”
Learning Placeholders for Open-Set Recognition (2021, background): “[40] considered open-set recognition as a sparse representation learning problem, and tried to match the reconstruction error distributions with extreme value theory (EVT) [12].”
Recent Advances in Open Set Recognition: A Survey (2018, methodology): “As reported in [61], although SROSR outperformed many competitive OSR algorithms, it also contains some limitations.”
Generalized Out-of-Distribution Detection: A Survey (2021, methodology): “Techniques such as sparsity concentration index [180] and kernel null space methods [181], [182] are used for sparse”
Learning and the Unknown: Surveying Steps toward Open World Recognition (2019, background): “The work in this area has received hundreds of citations from a wide range of application areas that need, or are using, OSR including: • Audio analysis (Battaglino, Lepauloux, and (Chiachia et al. 2014; Pinto et al. 2015; Rattani, Scheirer, and Ross 2015; Juefei-Xu and Savvides 2016; G¨unther et al”
Conditional Gaussian Distribution Learning for Open Set Recognition (2020, background): “[42] pointed out that discriminative information is mostly hidden in the reconstruction error distributions, and proposed the sparse representation-based OSR model, called SROSR.”
Classification-Reconstruction Learning for Open-Set Recognition (2018, background): “Among them, sparse-representation-based open-set recognition [48] shares the idea of reconstruction-based representation learning with ours.”
C2AE: Class Conditioned Auto-Encoder for Open-Set Recognition (2019, methodology): “There have been many methods that explore these questions in the context of traditional methods such as Support Vector Machines [35], [36], Nearest Neighbors [16], [3] and Sparse Representation [40].”
Learning Deep Features for One-Class Classification (2018, background): “as shown in Table 1. Majority of the past work have attempted to address the multi-class classiﬁcation [21], [16], [8] and detection problems [17], [39], [12]. While open-set classiﬁcation [32], [2], [40] has received some attention in recent years, little or no work has been done speciﬁcally target”
The Extreme Value Machine (2015, background): “open set recognition problems, where one- [11] and two-sided calibration models [12], [29] of decision boundaries lead to better generalization.”
Adversarial Reciprocal Points Learning for Open Set Recognition (2021, methodology): “Similar to the idea in [16], Yoshihashi et al.”
Multiple Class Novelty Detection Under Data Distribution Shift (2020, background): “Many problems such as countering adversarial/trojan/poison attacks [26,25,8,47], detecting novel categories [42,40,7,37,35,39] and out-of-distribution samples [13,24,10,54] etc. tackle diﬀerent aspects of robustness of CNNs.”