A plug-in attribute correction module for generalized zero-shot learning

نویسندگان

چکیده

• The first work that can correct attributes while preserving the original meaning of each attribute dimension. plug-in module aims to facilitate existing approaches and makes ZSL models eligible or even GZSL tasks. corrected better reflect visual contexts without losing integrability in attributes. While Zero Shot Learning recognize new classes training examples, they often fails incorporate both seen unseen together at test time, which is known as Generalized Zero-shot (GZSL) problem. This paper identifies a bottleneck issue when are not well-defined, reliable, inaccurate quantitative representations, suffering from visual-semantic discrepancy. We propose Generic Plug-in Attribute Correction (GPAC) effectively accommodate conventional Different embedding-based lose favor transparency attributes, our key challenge fully preserve make it complementary interpretable upgrade models. To this end, we novel nonnegative constraint with iterative Stochastic Gradient Descent toolbox fit GPAC into previous Extensive experiments on five popular datasets show method achieve state-of-the-art performance It also good practice for future incorporating prior human knowledge.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A 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 کامل

Generalized 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 کامل

Is Attribute-Based Zero-Shot Learning an Ill-Posed Strategy?

One transfer learning approach that has gained a wide popularity lately is attribute-based zero-shot learning. Its goal is to learn novel classes that were never seen during the training stage. The classical route towards realizing this goal is to incorporate a prior knowledge, in the form of a semantic embedding of classes, and to learn to predict classes indirectly via their semantic attribut...

متن کامل

LONG, LIU, SHAO: ATTRIBUTE EMBEDDING WITH VSAR FOR ZERO-SHOT LEARNING 1 Attribute Embedding with Visual-Semantic Ambiguity Removal for Zero-shot Learning

Conventional zero-shot learning (ZSL) methods recognise an unseen instance by projecting its visual features to a semantic space that is shared by both seen and unseen categories. However, we observe that such a one-way paradigm suffers from the visualsemantic ambiguity problem. Namely, the semantic concepts (e.g. attributes) cannot explicitly correspond to visual patterns, and vice versa. Such...

متن کامل

Ordinal Zero-Shot Learning

Zero-shot learning predicts new class even if no training data is available for that class. The solution to conventional zero-shot learning usually depends on side information such as attribute or text corpora. But these side information is not easy to obtain or use. Fortunately in many classification tasks, the class labels are ordered, and therefore closely related to each other. This paper d...

متن کامل

ذخیره 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: 2021

ISSN: ['1873-5142', '0031-3203']

DOI: https://doi.org/10.1016/j.patcog.2020.107767