ProTeCt: Prompt Tuning for Taxonomic Open Set Classification
This work addresses a specific bottleneck in adapting visual-language models for hierarchical classification tasks, representing an incremental advancement.
The paper tackles the problem of taxonomic open set classification, where existing prompt tuning methods often misclassify at coarser taxonomic levels despite correct leaf-level predictions, by proposing ProTeCt, a prompt tuning technique that calibrates hierarchical consistency, resulting in significant improvements in TOS classification without degrading leaf-level performance.
Visual-language foundation models, like CLIP, learn generalized representations that enable zero-shot open-set classification. Few-shot adaptation methods, based on prompt tuning, have been shown to further improve performance on downstream datasets. However, these methods do not fare well in the taxonomic open set (TOS) setting, where the classifier is asked to make predictions from label sets across different levels of semantic granularity. Frequently, they infer incorrect labels at coarser taxonomic class levels, even when the inference at the leaf level (original class labels) is correct. To address this problem, we propose a prompt tuning technique that calibrates the hierarchical consistency of model predictions. A set of metrics of hierarchical consistency, the Hierarchical Consistent Accuracy (HCA) and the Mean Treecut Accuracy (MTA), are first proposed to evaluate TOS model performance. A new Prompt Tuning for Hierarchical Consistency (ProTeCt) technique is then proposed to calibrate classification across label set granularities. Results show that ProTeCt can be combined with existing prompt tuning methods to significantly improve TOS classification without degrading the leaf level classification performance.