Universum-Inspired Supervised Contrastive Learning

Han, Aiyang; Geng, Chuanxing; Chen, Songcan

doi:10.1109/tip.2023.3290514

Cited by 5 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most recent advancements in this field explored the acquisition of universum through the application of Mixup . (Han, Geng, and Chen 2023) produced hard negatives in contrastive learning by Mixup-induced universum. (Zhang, Geng, and Chen 2022) used High-order Mixup for universum to re-balance the classes in long-tailed recognition.…”

Section: Universum Learningmentioning

confidence: 93%

All Beings Are Equal in Open Set Recognition

Li,

Zhang,

Geng

et al. 2024

AAAI

View full text Add to dashboard Cite

In open-set recognition (OSR), a promising strategy is exploiting pseudo-unknown data outside given K known classes as an additional K+1-th class to explicitly model potential open space. However, treating unknown classes without distinction is unequal for them relative to known classes due to the category-agnostic and scale-agnostic of the unknowns. This inevitably not only disrupts the inherent distributions of unknown classes but also incurs both class-wise and instance-wise imbalances between known and unknown classes. Ideally, the OSR problem should model the whole class space as K+∞, but enumerating all unknowns is impractical. Since the core of OSR is to effectively model the boundaries of known classes, this means just focusing on the unknowns nearing the boundaries of targeted known classes seems sufficient. Thus, as a compromise, we convert the open classes from infinite to K, with a novel concept Target-Aware Universum (TAU) and propose a simple yet effective framework Dual Contrastive Learning with Target-Aware Universum (DCTAU). In details, guided by the targeted known classes, TAU automatically expands the unknown classes from the previous 1 to K, effectively alleviating the distribution disruption and the imbalance issues mentioned above. Then, a novel Dual Contrastive (DC) loss is designed, where all instances irrespective of known or TAU are considered as positives to contrast with their respective negatives. Experimental results indicate DCTAU sets a new state-of-the-art.

show abstract

Section: Universum Learningmentioning

confidence: 93%