paper-with-me

Papers

MetricBERT: Text Representation Learning via Self-Supervised Triplet Training

2022-08-13 · Itzik Malkiel, Dvir Ginzburg, Oren Barkan, Avi Caciularu, Yoni Weill, Noam Koenigstein

We present MetricBERT, a BERT-based model that learns to embed text under a well-defined similarity metric while simultaneously adhering to the ``traditional'' masked-language task. We focus on downstream tasks of learning similarities for recommendations where we show that MetricBERT outperforms state-of-the-art alternatives, sometimes by a substantial margin. We conduct extensive evaluations of our method and its different variants, showing that our training objective is highly beneficial over a traditional contrastive loss, a standard cosine similarity objective, and six other baselines. As an additional contribution, we publish a dataset of video games descriptions along with a test set of similarity annotations crafted by a domain expert.

📄 PDF Abstract BibTeX arXiv:2208.06610

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningTriplet

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

TriBYOL: Triplet BYOL for Self-Supervised Representation Learning

2022-06-07 · Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama

This paper proposes a novel self-supervised learning method for learning better representations with small batch sizes. Many self-supervised learning methods based on certain forms of the siamese network have emerged and…

Representation LearningSelf-Supervised LearningTriplet

SimTriplet: Simple Triplet Representation Learning with a Single GPU

2021-03-09 · Quan Liu, Peter C. Louis, Yuzhe Lu, Aadarsh Jha 외

Contrastive learning is a key technique of modern self-supervised learning. The broader accessibility of earlier approaches is hindered by the need of heavy computational resources (e.g., at least 8 GPUs or 32 TPU cores)…

Contrastive LearningGPUMedical Image AnalysisRepresentation Learning+2

Leveraging triplet loss for unsupervised action segmentation

2023-04-13 · E. Bueno-Benito, B. Tura, M. Dimiccoli

In this paper, we propose a novel fully unsupervised framework that learns action representations suitable for the action segmentation task from the single input video itself, without requiring any training data. Our met…

Action SegmentationClusteringMetric LearningSegmentation+3

Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking

2023-12-14 · Shitong Sun, Fanghua Ye, Shaogang Gong

Composed image retrieval attempts to retrieve an image of interest from gallery images through a composed query of a reference image and its corresponding modified text. It has recently attracted attention due to the col…

Image RetrievalRerankingRe-RankingRetrieval+2

Trip-ROMA: Self-Supervised Learning with Triplets and Random Mappings

2021-07-22 · Wenbin Li, Xuesong Yang, Meihao Kong, Lei Wang 외

Contrastive self-supervised learning (SSL) methods, such as MoCo and SimCLR, have achieved great success in unsupervised visual representation learning. They rely on a large number of negative pairs and thus require eith…

Few-Shot LearningRepresentation LearningSelf-Supervised LearningTriplet+1