In this paper, we investigate the problem of retrieving images from a
database based on a multi-modal (image-text) query. Specifically, the query
text prompts some modification in the query image and the task is to retrieve
images with the desired modifications. For instance, a user of an E-Commerce
platform is interested in buying a dress, which should look similar to her
friend's dress, but the dress should be of white color with a ribbon sash. In
this case, we would like the algorithm to retrieve some dresses with desired
modifications in the query dress. We propose an autoencoder based model,
ComposeAE, to learn the composition of image and text query for retrieving
images. We adopt a deep metric learning approach and learn a metric that pushes
composition of source image and text query closer to the target images. We also
propose a rotational symmetry constraint on the optimization problem. Our
approach is able to outperform the state-of-the-art method TIRG \cite{TIRG} on
three benchmark datasets, namely: MIT-States, Fashion200k and Fashion IQ. In
order to ensure fair comparison, we introduce strong baselines by enhancing
TIRG method. To ensure reproducibility of the results, we publish our code
here: https://github.com/ecom-research/ComposeAE.

本文研究了基于多模态（图像 - 文本）查询的图像检索问题，提出了自编码器模型 ComposeAE，采用深度度量学习方法学习了推动源图像和文本查询组成更接近目标图像的度量，并在 MIT-States、Fashion200k 和 FashionIQ 三个基准数据集上优于当前最先进的 TIRG 方法。

图像检索中的图像 - 文本查询组合学习

Compositional Learning of Image-Text Query for Image Retrieval

Pose estimation is a widely explored problem, enabling many robotic tasks
such as grasping and manipulation. In this paper, we tackle the problem of pose
estimation for objects that exhibit rotational symmetry, which are common in
man-made and industrial environments. In particular, our aim is to infer poses
for objects not seen at training time, but for which their 3D CAD models are
available at test time. Previous work has tackled this problem by learning to
compare captured views of real objects with the rendered views of their 3D CAD
models, by embedding them in a joint latent space using neural networks. We
show that sidestepping the issue of symmetry in this scenario during training
leads to poor performance at test time. We propose a model that reasons about
rotational symmetry during training by having access to only a small set of
symmetry-labeled objects, whereby exploiting a large collection of unlabeled
CAD models. We demonstrate that our approach significantly outperforms a
naively trained neural network on a new pose dataset containing images of tools
and hardware.

本文介绍了如何使用旋转对称性来进行姿态估计，提出了一种能够通过训练来识别具有旋转对称性的物体的模型，使用未标记的 CAD 模型数据来提高算法性能，并在新的姿态数据集上测试了算法性能。

具有旋转对称性物体的姿态估计

Pose Estimation for Objects with Rotational Symmetry

Many classes of images exhibit rotational symmetry. Convolutional neural
networks are sometimes trained using data augmentation to exploit this, but
they are still required to learn the rotation equivariance properties from the
data. Encoding these properties into the network architecture, as we are
already used to doing for translation equivariance by using convolutional
layers, could result in a more efficient use of the parameter budget by
relieving the model from learning them. We introduce four operations which can
be inserted into neural network models as layers, and which can be combined to
make these models partially equivariant to rotations. They also enable
parameter sharing across different orientations. We evaluate the effect of
these architectural modifications on three datasets which exhibit rotational
symmetry and demonstrate improved performance with smaller models.

本文介绍了四种可以插入神经网络模型中的操作，并将它们组合起来使这些模型具有部分对称旋转性，并且使得神经网络可以在不同方向共享参数，从而达到更好的性能和模型尺寸。

利用卷积神经网络中的循环对称性

Exploiting Cyclic Symmetry in Convolutional Neural Networks

For a network of generic oscillators with nonlocal topology and
symmetry-breaking coupling we establish novel partially coherent inhomogeneous
spatial patterns, which combine the features of chimera states (coexisting
incongruous coherent and incoherent domains) and oscillation death (oscillation
suppression), which we call chimera death. We show that due to the interplay of
nonlocality and breaking of rotational symmetry by the coupling two distinct
scenarios from oscillatory behavior to a stationary state regime are possible:
a transition from an amplitude chimera to chimera death via in-phase
synchronized oscillations, and a direct abrupt transition for larger coupling
strength.

本文研究了具有非局部拓扑和破对称耦合的振荡器网络，发现了 chimera death 空间模式，结合了 chimera 状态（共存不相容的相干与不相干领域）和振荡死亡（振荡抑制）。我们发现，由于非局部性和耦合对旋转对称性的破坏的相互作用，从振荡行为到静态状态的转变有两种不同的情况。