Integrated generalized zero-shot learning for fine-grained classification
نویسندگان
چکیده
Embedding learning (EL) and feature synthesizing (FS) are two of the popular categories fine-grained GZSL methods. EL or FS using global features cannot discriminate fine details in absence local features. On other hand, methods exploiting either neglect direct attribute guidance information. Consequently, neither method performs well. In this paper, we propose to explore attribute-supervised visual for both an integrated manner GZSL. The proposed network has sub-network a sub-network. can be tested ways. We novel two-step dense attention mechanism discover attribute-guided introduce new mutual between sub-networks exploit mutually beneficial information optimization. Moreover, compute source-target class similarity based on transfer-learn target classes reduce bias towards source domain during testing. demonstrate that our outperforms contemporary benchmark datasets.
منابع مشابه
Zero-Shot Fine-Grained Classification by Deep Feature Learning with Semantics
Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task due to two main issues: lack of sufficient training data for every class and difficulty in learning discriminative features for representation. In this paper, to address the two issues, we propose a two-phase framework for recognizing images from unseen fine-grained classes, i.e. ...
متن کاملLabel Embedding for Zero-shot Fine-grained Named Entity Typing
Named entity typing is the task of detecting the types of a named entity in context. For instance, given “Eric is giving a presentation”, our goal is to infer that ‘Eric’ is a speaker or a presenter and a person. Existing approaches to named entity typing cannot work with a growing type set and fails to recognize entity mentions of unseen types. In this paper, we present a label embedding metho...
متن کاملZero-Shot Learning for Semantic Utterance Classification
We propose a novel zero-shot learning method for semantic utterance classification (SUC). It learns a classifier f : X → Y for problems where none of the semantic categories Y are present in the training set. The framework uncovers the link between categories and utterances through a semantic space. We show that this semantic space can be learned by deep neural networks trained on large amounts...
متن کاملA Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning
Prevalent techniques in zero-shot learning do not generalize well to other related problem scenarios. Here, we present a unified approach for conventional zero-shot, generalized zero-shot and few-shot learning problems. Our approach is based on a novel Class Adapting Principal Directions (CAPD) concept that allows multiple embeddings of image features into a semantic space. Given an image, our ...
متن کاملGeneralized Zero-Shot Learning via Synthesized Examples
We present a generative framework for generalized zeroshot learning where the training and test classes are not necessarily disjoint. Built upon a variational autoencoder based architecture, consisting of a probabilistic encoder and a probabilistic conditional decoder, our model can generate novel exemplars from seen/unseen classes, given their respective class attributes. These exemplars can s...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Pattern Recognition
سال: 2022
ISSN: ['1873-5142', '0031-3203']
DOI: https://doi.org/10.1016/j.patcog.2021.108246