Object detection is a fundamental problem in computer vision, aiming at
locating and classifying objects in image. Although current devices can easily
take very high-resolution images, current approaches of object detection seldom
consider detecting tiny object or the large scale variance problem in high
resolution images. In this paper, we introduce a simple yet efficient approach
that improves accuracy of object detection especially for small objects and
large scale variance scene while reducing the computational cost in high
resolution image. Inspired by observing that overall detection accuracy is
reduced if the image is properly down-sampled but the recall rate is not
significantly reduced. Besides, small objects can be better detected by
inputting high-resolution images even if using lightweight detector. We propose
a cluster-based coarse-to-fine object detection framework to enhance the
performance for detecting small objects while ensure the accuracy of large
objects in high-resolution images. For the first stage, we perform coarse
detection on the down-sampled image and center localization of small objects by
lightweight detector on high-resolution image, and then obtains image chips
based on cluster region generation method by coarse detection and center
localization results, and further sends chips to the second stage detector for
fine detection. Finally, we merge the coarse detection and fine detection
results. Our approach can make good use of the sparsity of the objects and the
information in high-resolution image, thereby making the detection more
efficient. Experiment results show that our proposed approach achieves
promising performance compared with other state-of-the-art detectors.

本文提出一种基于聚类的粗到细的目标检测框架，特别针对小物体和高分辨率图像的大规模差异问题，在提高目标检测准确率的同时降低了计算成本。

高分辨率图像物体检测的粗细粒度框架

A Coarse to Fine Framework for Object Detection in High Resolution Image

Topic models aim to reveal the latent structure behind a corpus, typically
conducted over a bag-of-words representation of documents. In the context of
topic modeling, most vocabulary is either irrelevant for uncovering underlying
topics or contains strong relationships with relevant concepts, impacting the
interpretability of these topics. Furthermore, their limited expressiveness and
dependency on language demand considerable computation resources. Hence, we
propose a novel approach for cluster-based topic modeling that employs
conceptual entities. Entities are language-agnostic representations of
real-world concepts rich in relational information. To this end, we extract
vector representations of entities from (i) an encyclopedic corpus using a
language model; and (ii) a knowledge base using a graph neural network. We
demonstrate that our approach consistently outperforms other state-of-the-art
topic models across coherency metrics and find that the explicit knowledge
encoded in the graph-based embeddings provides more coherent topics than the
implicit knowledge encoded with the contextualized embeddings of language
models.

我们提出了一种基于聚类的主题建模方法，使用概念实体作为语言无关的表示，并使用图神经网络从百科全书语料库和知识库中提取实体的向量表示，该方法在连贯性度量方面始终优于其他主题模型。

话题作为实体聚类：基于语言模型和图神经网络的基于实体的话题

Topics as Entity Clusters: Entity-based Topics from Language Models and Graph Neural Networks

We propose a cluster-based quantization method to convert pre-trained full
precision weights into ternary weights with minimal impact on the accuracy. In
addition, we also constrain the activations to 8-bits thus enabling sub 8-bit
full integer inference pipeline. Our method uses smaller clusters of N filters
with a common scaling factor to minimize the quantization loss, while also
maximizing the number of ternary operations. We show that with a cluster size
of N=4 on Resnet-101, can achieve 71.8% TOP-1 accuracy, within 6% of the best
full precision results while replacing ~85% of all multiplications with 8-bit
accumulations. Using the same method with 4-bit weights achieves 76.3% TOP-1
accuracy which within 2% of the full precision result. We also study the impact
of the size of the cluster on both performance and accuracy, larger cluster
sizes N=64 can replace ~98% of the multiplications with ternary operations but
introduces significant drop in accuracy which necessitates fine tuning the
parameters with retraining the network at lower precision. To address this we
have also trained low-precision Resnet-50 with 8-bit activations and ternary
weights by pre-initializing the network with full precision weights and achieve
68.9% TOP-1 accuracy within 4 additional epochs. Our final quantized model can
run on a full 8-bit compute pipeline, with a potential 16x improvement in
performance compared to baseline full-precision models.

本研究提出了一种基于聚类的量化方法，将预先训练好的全精度权重转换为三元权重，并将激活约束为 8 位，从而实现小于 8 位完整整数推理管道。此方法使用较小的 N 个过滤器的簇，并使用共同缩放因子来最小化量化损失，同时最大化三元操作的数量。在 ResNet-101 上使用 N=4 的簇大小，可以在替换了 85％的所有乘法运算为 8 位累加之后，实现 71.8％的 TOP-1 准确度。 使用 4 位权重的相同方法实现 76.3％，相对于全精度结果的误差不到 2％。同时，本研究还探讨了集群大小对性能和准确性的影响。 N=64 的较大集群大小可以使用三元操作替换 98％的乘法，但会显著降低准确性，需要在更低的精度下对参数进行微调和网络重新训练。为了解决这个问题，我们还使用全精度权重预初始化网络，通过 8 位激活和三元权重训练了低精度 ResNet-50，在额外的 4 个 epoch 内实现了 68.9％的 TOP-1 准确度。最终量化模型可以在完整的 8 位计算管道上运行，相对于基线全精度模型具有潜在的 16 倍性能提升。