使用基于CNN的编码器-解码器框架的压缩图像描述生成
Compressed Image Captioning using CNN-based Encoder-Decoder Framework
AI总结：
本研究提出结合CNN与编码器-解码器模型的自动图像描述生成架构，通过实验预训练模型并引入频率正则化技术压缩AlexNet和EfficientNetB0，在保持描述生成有效性的同时提升资源效率。
摘要：
在当今世界，图像处理在从科学研究到工业应用的各个领域都发挥着至关重要的作用。其中一个特别令人兴奋的应用是图像描述生成。有效的图像描述生成具有巨大的潜在影响。它可以显著提高搜索引擎的准确性，使查找相关信息变得更加容易。此外，它可以极大地增强视障人士的可访问性，为他们提供更具沉浸感的数字内容体验。然而，尽管前景广阔，图像描述生成仍面临若干挑战。一个主要障碍是从图像中提取有意义的视觉信息并将其转化为连贯的语言。这需要弥合视觉与语言领域之间的差距，这项任务需要复杂的算法和模型。我们的项目旨在通过开发一种自动图像描述生成架构来解决这些挑战，该架构结合了卷积神经网络（CNNs）和编码器-解码器模型的优势。CNN模型用于从图像中提取视觉特征，随后在编码器-解码器框架的帮助下生成描述。我们还进行了性能比较，深入研究了预训练CNN模型领域，试验了多种架构以了解它们的性能差异。在追求优化的过程中，我们还探索了集成频率正则化技术来压缩“AlexNet”和“EfficientNetB0”模型。我们旨在观察这种压缩模型是否能在生成图像描述方面保持其有效性，同时更加节省资源。
英文摘要：
In today's world, image processing plays a crucial role across various fields, from scientific research to industrial applications. But one particularly exciting application is image captioning. The potential impact of effective image captioning is vast. It can significantly boost the accuracy of search engines, making it easier to find relevant information. Moreover, it can greatly enhance accessibility for visually impaired individuals, providing them with a more immersive experience of digital content. However, despite its promise, image captioning presents several challenges. One major hurdle is extracting meaningful visual information from images and transforming it into coherent language. This requires bridging the gap between the visual and linguistic domains, a task that demands sophisticated algorithms and models. Our project is focused on addressing these challenges by developing an automatic image captioning architecture that combines the strengths of convolutional neural networks (CNNs) and encoder-decoder models. The CNN model is used to extract the visual features from images, and later, with the help of the encoder-decoder framework, captions are generated. We also did a performance comparison where we delved into the realm of pre-trained CNN models, experimenting with multiple architectures to understand their performance variations. In our quest for optimization, we also explored the integration of frequency regularization techniques to compress the "AlexNet" and "EfficientNetB0" model. We aimed to see if this compressed model could maintain its effectiveness in generating image captions while being more resource-efficient.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
