Image-Text Retrieval (ITR) is essentially a ranking problem. Given a query
caption, the goal is to rank candidate images by relevance, from large to
small. The current ITR datasets are constructed in a pairwise manner.
Image-text pairs are annotated as positive or negative. Correspondingly, ITR
models mainly use pairwise losses, such as triplet loss, to learn to rank.
Pairwise-based ITR increases positive pair similarity while decreasing negative
pair similarity indiscriminately. However, the relevance between dissimilar
negative pairs is different. Pairwise annotations cannot reflect this
difference in relevance. In the current datasets, pairwise annotations miss
many correlations. There are many potential positive pairs among the pairs
labeled as negative. Pairwise-based ITR can only rank positive samples before
negative samples, but cannot rank negative samples by relevance. In this paper,
we integrate listwise ranking into conventional pairwise-based ITR. Listwise
ranking optimizes the entire ranking list based on relevance scores.
Specifically, we first propose a Relevance Score Calculation (RSC) module to
calculate the relevance score of the entire ranked list. Then we choose the
ranking metric, Normalized Discounted Cumulative Gain (NDCG), as the
optimization objective. We transform the non-differentiable NDCG into a
differentiable listwise loss, named Smooth-NDCG (S-NDCG). Our listwise ranking
approach can be plug-and-play integrated into current pairwise-based ITR
models. Experiments on ITR benchmarks show that integrating listwise ranking
can improve the performance of current ITR models and provide more
user-friendly retrieval results. The code is available at
this https URL

本文提出了在传统基于成对注释的图像 - 文本检索（ITR）中，集成列表式排名以提高检索性能和提供更用户友好的检索结果的方法。具体而言，该方法采用 Relevance Score Calculation（RSC）模块计算整个排名列表的相关分数，并选择标准化折现累积增益（NDCG）作为优化目标，将不可微分的 NDCG 转化为可微分的列表式损失 ——Smooth-NDCG（S-NDCG）。实验表明，该列表式排序方法可以插入并成为现有成对注释的 ITR 模型的一部分，提高了现有 ITR 模型的性能。

将利用列表法排序与基于对比法的图像 - 文本检索相融合

Integrating Listwise Ranking into Pairwise-based Image-Text Retrieval

Object re-identification (ReID) aims to find instances with the same identity
as the given probe from a large gallery. Pairwise losses play an important role
in training a strong ReID network. Existing pairwise losses densely exploit
each instance as an anchor and sample its triplets in a mini-batch. This dense
sampling mechanism inevitably introduces positive pairs that share few visual
similarities, which can be harmful to the training. To address this problem, we
propose a novel loss paradigm termed Sparse Pairwise (SP) loss that only
leverages few appropriate pairs for each class in a mini-batch, and empirically
demonstrate that it is sufficient for the ReID tasks. Based on the proposed
loss framework, we propose an adaptive positive mining strategy that can
dynamically adapt to diverse intra-class variations. Extensive experiments show
that SP loss and its adaptive variant AdaSP loss outperform other pairwise
losses, and achieve state-of-the-art performance across several ReID
benchmarks. Code is available at this https URL

提出了一种基于少量样本对的新损失范式，稀疏成对（SP）损失，以及一个新的适应性正类挖掘策略，自适应稀疏成对损失（AdaSP）损失，用于对象重新识别，具有优于其他成对损失的表现，达到了几个重新识别基准的最新水平 。