DeepAI AI Chat
Log In Sign Up

Ladder Loss for Coherent Visual-Semantic Embedding

11/18/2019
by   Mo Zhou, et al.
Xi'an Jiaotong University
0

For visual-semantic embedding, the existing methods normally treat the relevance between queries and candidates in a bipolar way – relevant or irrelevant, and all "irrelevant" candidates are uniformly pushed away from the query by an equal margin in the embedding space, regardless of their various proximity to the query. This practice disregards relatively discriminative information and could lead to suboptimal ranking in the retrieval results and poorer user experience, especially in the long-tail query scenario where a matching candidate may not necessarily exist. In this paper, we introduce a continuous variable to model the relevance degree between queries and multiple candidates, and propose to learn a coherent embedding space, where candidates with higher relevance degrees are mapped closer to the query than those with lower relevance degrees. In particular, the new ladder loss is proposed by extending the triplet loss inequality to a more general inequality chain, which implements variable push-away margins according to respective relevance degrees. In addition, a proper Coherent Score metric is proposed to better measure the ranking results including those "irrelevant" candidates. Extensive experiments on multiple datasets validate the efficacy of our proposed method, which achieves significant improvement over existing state-of-the-art methods.

READ FULL TEXT
10/20/2022

Image-Text Retrieval with Binary and Continuous Label Supervision

Most image-text retrieval work adopts binary labels indicating whether a...
04/16/2020

Multiple Visual-Semantic Embedding for Video Retrieval from Query Sentence

Visual-semantic embedding aims to learn a joint embedding space where re...
04/27/2022

Relevance-based Margin for Contrastively-trained Video Retrieval Models

Video retrieval using natural language queries has attracted increasing ...
08/06/2020

Efficient Neural Query Auto Completion

Query Auto Completion (QAC), as the starting point of information retrie...
04/25/2022

LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback

Pseudo-relevance feedback (PRF) has proven to be an effective query refo...
11/17/2020

Improving Calibration in Deep Metric Learning With Cross-Example Softmax

Modern image retrieval systems increasingly rely on the use of deep neur...
06/15/2019

Relevance Feedback with Latent Variables in Riemann spaces

In this paper we develop and evaluate two methods for relevance feedback...