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

Alabdulmohsin, Ibrahim; Cissé, Moustapha; Zhang, Xiangliang

doi:10.1007/978-3-319-46128-1_47

Cited by 4 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use the IVFPQ implementation from the FAISS open source library. 1 We use 4, 096 centroids and 8 probes for the inverted file. Unless said otherwise, we query the 1, 024 nearest neighbors.…”

Section: Implementation Detailsmentioning

confidence: 99%

See 1 more Smart Citation

Unbounded cache model for online language modeling with open vocabulary

Grave¹,

Cissé²,

Joulin³

2017

Preprint

Self Cite

View full text Add to dashboard Cite

Recently, continuous cache models were proposed as extensions to recurrent neural network language models, to adapt their predictions to local changes in the data distribution. These models only capture the local context, of up to a few thousands tokens. In this paper, we propose an extension of continuous cache models, which can scale to larger contexts. In particular, we use a large scale non-parametric memory component that stores all the hidden activations seen in the past. We leverage recent advances in approximate nearest neighbor search and quantization algorithms to store millions of representations while searching them efficiently. We conduct extensive experiments showing that our approach significantly improves the perplexity of pre-trained language models on new distributions, and can scale efficiently to much larger contexts than previously proposed local cache models.This solution has been used in speech recognition under the name of cache models [36,37]. Cache models exploit the unigram distribution of a recent context to improve the predictive ability of the model. Recently, Grave et al. [22] and Merity et al. [43] showed that this solution could be applied to neural networks. However, cache models depend on the local context. Hence, they can only adapt a parametric model to a local change in the distribution. These specificities limit their usefulness when 31st Conference on Neural Information Processing Systems (NIPS 2017),

show abstract

Section: Implementation Detailsmentioning

confidence: 99%

“…However, their approach relies on unrealistic assumptions on the data distribution. Zero-shot learning [41] can deal with new classes but often requires additional descriptive information about them [1]. Scheirer et al [49] proposed a framework for open set recognition based on one-class SVMs.…”

Section: Introductionmentioning

confidence: 99%

Unbounded cache model for online language modeling with open vocabulary

Grave¹,

Cissé²,

Joulin³

2017

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In particular, we refer here to the zero-shot learning, where the classes covered by training and testing samples are disjoint [13,14].…”

Section: Introductionmentioning

confidence: 99%

Zero-Shot Human Activity Recognition Using Non-Visual Sensors

Machot

Elkobaisi

Kyamakya

2020

Sensors

View full text Add to dashboard Cite

Due to significant advances in sensor technology, studies towards activity recognition have gained interest and maturity in the last few years. Existing machine learning algorithms have demonstrated promising results by classifying activities whose instances have been already seen during training. Activity recognition methods based on real-life settings should cover a growing number of activities in various domains, whereby a significant part of instances will not be present in the training data set. However, to cover all possible activities in advance is a complex and expensive task. Concretely, we need a method that can extend the learning model to detect unseen activities without prior knowledge regarding sensor readings about those previously unseen activities. In this paper, we introduce an approach to leverage sensor data in discovering new unseen activities which were not present in the training set. We show that sensor readings can lead to promising results for zero-shot learning, whereby the necessary knowledge can be transferred from seen to unseen activities by using semantic similarity. The evaluation conducted on two data sets extracted from the well-known CASAS datasets show that the proposed zero-shot learning approach achieves a high performance in recognizing unseen (i.e., not present in the training dataset) new activities.

show abstract

“…Zero-shot learning is the problem of recognizing novel categories of data when no prior information is available during the training phase [2,3,4]. One practical approach to such transfer learning is the incorporation of semantic attributes as descriptive features to map the input data to an intermediate semantic space, which can discriminate between different unseen categories [3,4].…”

Section: Introductionmentioning

confidence: 99%

Multiple-Kernel Dictionary Learning for Reconstruction and Clustering of Unseen Multivariate Time-series

Hosseini,

Hammer

2019

Preprint

View full text Add to dashboard Cite

There exist many approaches for description and recognition of unseen classes in datasets. Nevertheless, it becomes a challenging problem when we deal with multivariate time-series (MTS) (e.g., motion data), where we cannot apply the vectorial algorithms directly to the inputs. In this work, we propose a novel multiple-kernel dictionary learning (MKD) which learns semantic attributes based on specific combinations of MTS dimensions in the feature space. Hence, MKD can fully/partially reconstructs the unseen classes based on the training data (seen classes). Furthermore, we obtain sparse encodings for unseen classes based on the learned MKD attributes, and upon which we propose a simple but effective incremental clustering algorithm to categorize the unseen MTS classes in an unsupervised way. According to the empirical evaluation of our MKD framework on real benchmarks, it provides an interpretable reconstruction of unseen MTS data as well as a high performance regarding their online clustering.

show abstract

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

Cited by 4 publications

References 14 publications

Unbounded cache model for online language modeling with open vocabulary

Unbounded cache model for online language modeling with open vocabulary

Zero-Shot Human Activity Recognition Using Non-Visual Sensors

Multiple-Kernel Dictionary Learning for Reconstruction and Clustering of Unseen Multivariate Time-series

Contact Info

Product

Resources

About