paper-with-me

홈 › Papers

Improving filling level classification with adversarial training

2021-02-08 · Apostolos Modas, Alessio Xompero, Ricardo Sanchez-Matilla, Pascal Frossard, Andrea Cavallaro

We investigate the problem of classifying - from a single image - the level of content in a cup or a drinking glass. This problem is made challenging by several ambiguities caused by transparencies, shape variations and partial occlusions, and by the availability of only small training datasets. In this paper, we tackle this problem with an appropriate strategy for transfer learning. Specifically, we use adversarial training in a generic source dataset and then refine the training with a task-specific dataset. We also discuss and experimentally evaluate several training strategies and their combination on a range of container types of the CORSMAL Containers Manipulation dataset. We show that transfer learning with adversarial training in the source domain consistently improves the classification accuracy on the test set and limits the overfitting of the classifier to specific features of the training data.

📄 PDF Abstract BibTeX arXiv:2102.04057

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral ClassificationTransfer Learning

Similar Papers 제목 키워드 기반

Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling

2020-12-01 · COLING 2020 8 · Xu Cao, Deyi Xiong, Chongyang Shi, Chao Wang 외

Joint intent detection and slot filling has recently achieved tremendous success in advancing the performance of utterance understanding. However, many joint models still suffer from the robustness problem, especially on…

Intent Detectionslot-fillingSlot Filling

Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding

2017-11-30 · Bing Liu, Ian Lane

The goal of this paper is to learn cross-domain representations for slot filling task in spoken language understanding (SLU). Most of the recently published SLU models are domain-specific ones that work on individual tas…

slot-fillingSlot FillingSpoken Language Understanding

BERT for Joint Intent Classification and Slot Filling

2019-02-28 · Qian Chen, Zhu Zhuo, Wen Wang

Intent classification and slot filling are two essential tasks for natural language understanding. They often suffer from small-scale human-labeled training data, resulting in poor generalization capability, especially f…

General Classificationintent-classificationIntent ClassificationIntent Detection+3

Bi-directional Joint Neural Networks for Intent Classification and Slot Filling

2022-02-26 · Soyeon Caren Han, Siqu Long, Huichun Li, Henry Weld 외

Intent classification and slot filling are two critical tasks for natural language understanding. Traditionally the two tasks proceeded independently. However, more recently joint models for intent classification and slo…

Classificationintent-classificationIntent ClassificationIntent Classification and Slot Filling+4

Simple is Better! Lightweight Data Augmentation for Low Resource Slot Filling and Intent Classification

2020-09-08 · PACLIC 2020 10 · Samuel Louvan, Bernardo Magnini

Neural-based models have achieved outstanding performance on slot filling and intent classification, when fairly large in-domain training data are available. However, as new domains are frequently added, creating sizeabl…

Data AugmentationGeneral Classificationintent-classificationIntent Classification+3