paper-with-me

홈 › Papers

Learning More Universal Representations for Transfer-Learning

2017-12-27 · Youssef Tamaazousti, Hervé Le Borgne, Céline Hudelot, Mohamed El Amine Seddik, Mohamed Tamaazousti

A representation is supposed universal if it encodes any element of the visual world (e.g., objects, scenes) in any configuration (e.g., scale, context). While not expecting pure universal representations, the goal in the literature is to improve the universality level, starting from a representation with a certain level. To do so, the state-of-the-art consists in learning CNN-based representations on a diversified training problem (e.g., ImageNet modified by adding annotated data). While it effectively increases universality, such approach still requires a large amount of efforts to satisfy the needs in annotated data. In this work, we propose two methods to improve universality, but pay special attention to limit the need of annotated data. We also propose a unified framework of the methods based on the diversifying of the training problem. Finally, to better match Atkinson's cognitive study about universal human representations, we proposed to rely on the transfer-learning scheme as well as a new metric to evaluate universality. This latter, aims us to demonstrates the interest of our methods on 10 target-problems, relating to the classification task and a variety of visual domains.

📄 PDF Abstract BibTeX arXiv:1712.09708

Code (1)

youssefTamaazousti/MulDiPNet tf

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

Cross-lingual Semantic Role Labeling with Model Transfer

2020-08-24 · Hao Fei, Meishan Zhang, Fei Li, Donghong Ji

Prior studies show that cross-lingual semantic role labeling (SRL) can be achieved by model transfer under the help of universal features. In this paper, we fill the gap of cross-lingual SRL by proposing an end-to-end SR…

Semantic Role Labeling

Universal Successor Representations for Transfer Reinforcement Learning

2018-04-11 · Chen Ma, Junfeng Wen, Yoshua Bengio

The objective of transfer reinforcement learning is to generalize from a set of previous tasks to unseen new tasks. In this work, we focus on the transfer scenario where the dynamics among tasks are the same, but their g…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Transfer Learning+1

Towards Universal Sequence Representation Learning for Recommender Systems

2022-06-13 · Yupeng Hou, Shanlei Mu, Wayne Xin Zhao, Yaliang Li 외

In order to develop effective sequential recommenders, a series of sequence representation learning (SRL) methods are proposed to model historical user behaviors. Most existing SRL methods rely on explicit item IDs for d…

Mixture-of-ExpertsRecommendation SystemsRepresentation Learning

SufiSent - Universal Sentence Representations Using Suffix Encodings

2018-02-20 · Siddhartha Brahma

Computing universal distributed representations of sentences is a fundamental task in natural language processing. We propose a method to learn such representations by encoding the suffixes of word sequences in a sentenc…

Natural Language InferenceSentence

Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

2017-05-05 · EMNLP 2017 9 · Alexis Conneau, Douwe Kiela, Holger Schwenk, Loic Barrault 외

Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however no…

Cross-Lingual Natural Language InferenceNatural Language InferenceSemantic Textual SimilaritySentence+2