From Generalized zero-shot learning to long-tail with class descriptors
Real-world data is predominantly unbalanced and long-tailed, but deep models struggle to recognize rare classes in the presence of frequent classes. Often, classes can be accompanied by side information like textual descriptions, but it is not fully clear how to use them for learning with unbalanced long-tail data. Such descriptions have been mostly used in (Generalized) Zero-shot learning (ZSL), suggesting that ZSL with class descriptions may also be useful for long-tail distributions. We describe DRAGON, a late-fusion architecture for long-tail learning with class descriptors. It learns to (1) correct the bias towards head classes on a sample-by-sample basis; and (2) fuse information from class-descriptions to improve the tail-class accuracy. We also introduce new benchmarks CUB-LT, SUN-LT, AWA-LT for long-tail learning with class-descriptions, building on existing learning-with-attributes datasets and a version of Imagenet-LT with class descriptors. DRAGON outperforms state-of-the-art models on the new benchmark. It is also a new SoTA on existing benchmarks for GFSL with class descriptors (GFSL-d) and standard (vision-only) long-tailed learning ImageNet-LT, CIFAR-10, 100, and Places365.
Code (1)
Tasks
Few-Shot LearningGeneralized Few-Shot LearningGeneralized Zero-Shot LearningLong-tail LearningLong-tail learning with class descriptorsZero-Shot LearningSimilar Papers 제목 키워드 기반
Learn from Anywhere: Rethinking Generalized Zero-Shot Learning with Limited Supervision
A common problem with most zero and few-shot learning approaches is they suffer from bias towards seen classes resulting in sub-optimal performance. Existing efforts aim to utilize unlabeled images from unseen classes (i…
Few-Shot LearningGeneralized Zero-Shot LearningZero-Shot LearningGeneralized Zero-shot ICD Coding
The International Classification of Diseases (ICD) is a list of classification codes for the diagnoses. Automatic ICD coding is in high demand as the manual coding can be labor-intensive and error-prone. It is a multi-la…
ClassificationGeneral ClassificationGeneralized Zero-Shot LearningMulti Label Text Classification+4Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space. As labeled images are expensive, one direction is to augment the dataset by gen…
Few-Shot LearningGeneralized Few-Shot LearningGeneralized Zero-Shot LearningZero-Shot Learning+1Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space. As labeled images are expensive, one direction is to augment the dataset by gen…
Few-Shot LearningGeneralized Few-Shot LearningGeneralized Zero-Shot LearningGeneralized Zero-Shot Learning - Unseen+2Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models
Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one. Thus, to enhance the performance, fi…