Not identical but similar objects are everywhere in the world. Examples
include four-legged animals such as dogs and cats, cars of different models,
akin flowers in various colors, and countless others. In this study, we address
a novel task of matching such non-identical objects. We propose a simple
weighting scheme of descriptors that enhance various sparse image matching
methods, which are originally designed for matching identical objects captured
from different perspectives, and achieve semantically robust matching. The
experiments show successful matching between non-identical objects in various
cases including domain shift. Further, we present a first evaluation of the
robustness of the image matching methods under common corruptions, which is a
sort of domain shift, and the proposed method improves the matching in this
case as well.

我们提出了一种简单的描述符加权方案，可以增强不同角度捕捉到的非相同物体的稀疏图像匹配方法，在各种情况下实现了语义鲁棒的匹配。此外，我们首次评估了图像匹配方法在常见破坏下的鲁棒性，即一种域偏移，该方法在这种情况下提高了匹配效果。

匹配非相同物体

Matching Non-Identical Objects

Diffusion models learn to restore noisy data, which is corrupted with
different levels of noise, by optimizing the weighted sum of the corresponding
loss terms, i.e., denoising score matching loss. In this paper, we show that
restoring data corrupted with certain noise levels offers a proper pretext task
for the model to learn rich visual concepts. We propose to prioritize such
noise levels over other levels during training, by redesigning the weighting
scheme of the objective function. We show that our simple redesign of the
weighting scheme significantly improves the performance of diffusion models
regardless of the datasets, architectures, and sampling strategies.

本文研究了扩散模型学习以优化对应丢失函数的加权和（去噪得分匹配损失）来恢复不同噪声水平的嘈杂数据，并提出了恢复受特定噪声水平损坏的数据作为学习丰富视觉概念的适当预先任务的方法，通过重新设计目标函数的加权方案，在训练过程中优先考虑这些噪声水平，我们证明了我们简单的加权方案重构可以显著提高扩散模型的性能。

感知优先的弥散模型训练

Perception Prioritized Training of Diffusion Models

Query expansion (QE) is a well-known technique used to enhance the
effectiveness of information retrieval. QE reformulates the initial query by
adding similar terms that help in retrieving more relevant results. Several
approaches have been proposed in literature producing quite favorable results,
but they are not evenly favorable for all types of queries (individual and
phrase queries). One of the main reasons for this is the use of the same kind
of data sources and weighting scheme while expanding both the individual and
the phrase query terms. As a result, the holistic relationship among the query
terms is not well captured or scored. To address this issue, we have presented
a new approach for QE using Wikipedia and WordNet as data sources.
Specifically, Wikipedia gives rich expansion terms for phrase terms, while
WordNet does the same for individual terms. We have also proposed novel
weighting schemes for expansion terms: in-link score (for terms extracted from
Wikipedia) and a tf-idf based scheme (for terms extracted from WordNet). In the
proposed Wikipedia-WordNet-based QE technique (WWQE), we weigh the expansion
terms twice: first, they are scored by the weighting scheme individually, and
then, the weighting scheme scores the selected expansion terms concerning the
entire query using correlation score. The proposed approach gains improvements
of 24% on the MAP score and 48% on the GMAP score over unexpanded queries on
the FIRE dataset. Experimental results achieve a significant improvement over
individual expansion and other related state-of-the-art approaches. We also
analyzed the effect on retrieval effectiveness of the proposed technique by
varying the number of expansion terms.

使用维基百科和 WordNet 作为数据源，本研究提出了一种新的查询扩展技术，并采用新的加权方案，获得 24% 的 MAP 分数和 48% 的 GMAP 分数提升。