COSTA: Co-Occurrence Statistics for Zero-Shot Classification
In this paper we aim for zero-shot classification, that is visual recognition of an unseen class by using knowledge transfer from known classes. Our main contribution is COSTA, which exploits co-occurrences of visual concepts in images for knowledge transfer. These inter-dependencies arise naturally between concepts, and are easy to obtain from existing annotations or web-search hit counts. We estimate a classifier for a new label, as a weighted combination of related classes, using the co-occurrences to define the weight. We propose various metrics to leverage these co-occurrences, and a regression model for learning a weight for each related class. We also show that our zero-shot classifiers can serve as priors for few-shot learning. Experiments on three multi-labeled datasets reveal that our proposed zero-shot methods, are approaching and occasionally outperforming fully supervised SVMs. We conclude that co-occurrence statistics suffice for zero-shot classification.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationFew-Shot LearningGeneral ClassificationTransfer Learningzero-shot-classificationZero-Shot LearningSimilar Papers 제목 키워드 기반
Sign Languages and the Online World Online Dictionaries \& Lexicostatistics
X-Shot: A Unified System to Handle Frequent, Few-shot and Zero-shot Learning Simultaneously in Classification
In recent years, few-shot and zero-shot learning, which learn to predict labels with limited annotated instances, have garnered significant attention. Traditional approaches often treat frequent-shot (freq-shot; labels w…
Domain GeneralizationInstruction FollowingZero-Shot LearningmPLM-Sim: Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Models
Recent multilingual pretrained language models (mPLMs) have been shown to encode strong language-specific signals, which are not explicitly provided during pretraining. It remains an open question whether it is feasible …
Cross-Lingual TransferOpen-Ended Question AnsweringZero-Shot Cross-Lingual TransferZero-Shot Crowd Behavior Recognition
Understanding crowd behavior in video is challenging for computer vision. There have been increasing attempts on modeling crowded scenes by introducing ever larger property ontologies (attributes) and annotating ever lar…
AttributeZero-Shot LearningProtoCLIP: Prototype-Aligned Latent Refinement for Robust Zero-Shot Chest X-Ray Classification
Zero-shot vision-language models (VLMs) have shown promise for chest radiograph classification, but their performance is often limited by confounding label co-occurrence, long-tail class imbalance, and transfer instabili…