Hierarchical Selective Classification
Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces hierarchical selective classification, extending selective classification to a hierarchical setting. Our approach leverages the inherent structure of class relationships, enabling models to reduce the specificity of their predictions when faced with uncertainty. In this paper, we first formalize hierarchical risk and coverage, and introduce hierarchical risk-coverage curves. Next, we develop algorithms for hierarchical selective classification (which we refer to as "inference rules"), and propose an efficient algorithm that guarantees a target accuracy constraint with high probability. Lastly, we conduct extensive empirical studies on over a thousand ImageNet classifiers, revealing that training regimes such as CLIP, pretraining on ImageNet21k and knowledge distillation boost hierarchical selective performance.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationKnowledge DistillationSpecificityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DEEP HIERARCHICAL MODEL FOR HIERARCHICAL SELECTIVE CLASSIFICATION AND ZERO SHOT LEARNING
Object recognition in real-world image scenes is still an open problem. With the growing number of classes, the similarity structures between them become complex and the distinction between classes blurs, which makes the…
ClassificationObject RecognitionRetrievalZero-Shot LearningMaking Language Model a Hierarchical Classifier and Generator
Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by human's hierarchical thinking capability, we propose that a hierarchical decoder architecture could be built with diff…
DecoderLanguage ModelingLanguage Modellingmodel+3Classification of hierarchical text using geometric deep learning: the case of clinical trials corpus
We consider the hierarchical representation of documents as graphs and use geometric deep learning to classify them into different categories. While graph neural networks can efficiently handle the variable structure of …
Probabilistic Selective Encryption of Convolutional Neural Networks for Hierarchical Services
Model protection is vital when deploying Convolutional Neural Networks (CNNs) for commercial services, due to the massive costs of training them. In this work, we propose a selective encryption (SE) algorithm to protect …
DenoisingOn the Selective and Invariant Representation of DCNN for High-Resolution Remote Sensing Image Recognition
Human vision possesses strong invariance in image recognition. The cognitive capability of deep convolutional neural network (DCNN) is close to the human visual level because of hierarchical coding directly from raw imag…
General ClassificationScene Recognition