面向压缩学习的习得式压缩
Learned Compression for Compressed Learning
AI总结：
针对现有压缩系统不适用于压缩学习的问题，提出结合线性变换编码与非线性降维自编码器的WaLLoC神经编解码器，在多项指标上优于现有自编码器，且效率高、模态兼容性强，可应用于多类压缩域学习任务。
摘要：
现代传感器生成的高分辨率数据流日益丰富。受资源限制，机器学习系统通过降低分辨率丢弃了其中绝大多数信息。压缩域学习允许模型在紧凑的潜在表征上运行，从而在相同预算下实现更高的有效分辨率。然而，现有压缩系统并不适用于压缩学习。线性变换编码和端到端习得式压缩系统虽降低了比特率，但并未均匀降低维度，因此无法有效提升效率。生成式自编码器可降低维度，但其对抗性或感知目标会导致显著的信息损失。为解决这些局限，我们提出WaLLoC（小波习得式有损压缩），这是一种结合线性变换编码与非线性降维自编码器的神经编解码器架构。WaLLoC在可逆小波包变换之间嵌入了一个浅层非对称自编码器和熵瓶颈。在多项关键指标上，WaLLoC的表现优于当前最先进的潜在扩散模型中使用的自编码器。WaLLoC无需感知损失或对抗损失即可表征高频细节，因此可兼容RGB图像和立体音频之外的多种模态。WaLLoC的编码器几乎完全由线性运算构成，效率极高，适用于移动计算、遥感以及直接从压缩数据中学习的场景。我们在图像分类、上色、文档理解和音乐源分离等多项任务中验证了WaLLoC在压缩域学习方面的能力。我们的代码、实验以及预训练的音频和图像编解码器可在https://ut-sysml.org/walloc获取。
英文摘要：
Modern sensors produce increasingly rich streams of high-resolution data. Due to resource constraints, machine learning systems discard the vast majority of this information via resolution reduction. Compressed-domain learning allows models to operate on compact latent representations, allowing higher effective resolution for the same budget. However, existing compression systems are not ideal for compressed learning. Linear transform coding and end-to-end learned compression systems reduce bitrate, but do not uniformly reduce dimensionality; thus, they do not meaningfully increase efficiency. Generative autoencoders reduce dimensionality, but their adversarial or perceptual objectives lead to significant information loss. To address these limitations, we introduce WaLLoC (Wavelet Learned Lossy Compression), a neural codec architecture that combines linear transform coding with nonlinear dimensionality-reducing autoencoders. WaLLoC sandwiches a shallow, asymmetric autoencoder and entropy bottleneck between an invertible wavelet packet transform. Across several key metrics, WaLLoC outperforms the autoencoders used in state-of-the-art latent diffusion models. WaLLoC does not require perceptual or adversarial losses to represent high-frequency detail, providing compatibility with modalities beyond RGB images and stereo audio. WaLLoC's encoder consists almost entirely of linear operations, making it exceptionally efficient and suitable for mobile computing, remote sensing, and learning directly from compressed data. We demonstrate WaLLoC's capability for compressed-domain learning across several tasks, including image classification, colorization, document understanding, and music source separation. Our code, experiments, and pre-trained audio and image codecs are available at https://ut-sysml.org/walloc
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。
