Underwater salient object detection (USOD) is important for marine exploration, ecological monitoring, and autonomous underwater vehicle navigation. However, the performance of existing methods remains limited by underwater optical distortions, color casts, and the absence of reliable depth sensing. To address these challenges, we propose the Underwater Depth-Fused Saliency Network (UDF-Net), a framework that couples self-supervised monocular depth estimation with attention-based multimodal fusion. To overcome the limitations of RGB-only USOD, UDF-Net utilizes a CNN-based encoder-decoder architecture combined with a lightweight multi-view transformer to effectively estimate depth from a single underwater RGB image. Given the lack of ground-truth depth underwater, we derive a physics-based self-supervisory signal by generating pseudo-depth via a generalized dark-channel prior. An attention-aware fusion module then enables fine-grained interaction between the RGB and depth modalities, while a task-driven joint optimization strategy trains saliency detection and depth estimation end-to-end to enforce semantic consistency and robustness. Extensive experiments on various USOD datasets demonstrate that UDF-Net significantly surpasses state-of-the-art models in accuracy and robustness.

Ensuring service availability in large-scale datacenters hinges on network monitoring. For monitoring quality, it is essential to attain sufficient coverage of all physical components. However, given the ever-evolving complexity of industrial environments, even measuring coverage metrics becomes challenging, let alone attaining sufficient coverage. In fact, insufficient coverage widely existed in our production datacenters and caused many missed failures.

Sketch algorithms have been widely deployed for network measurement as they achieve high accuracy with restricted resource usage. They store measurement results compactly in fixed-size counters. However, as sketch counters are skewed towards low values, higher bits in most counters remain zero. Such massive unused bits impair the space efficiency valued by sketch algorithms. Unfortunately, efforts to mitigate the issue either apply to specific algorithms or compromise accuracy. In this paper, we design BitSense, a novel optimization framework that integrates with existing sketch algorithms. The key idea is to regard higher bits in sketch counters as a sparse vector and leverage compressive sensing techniques to compress and restore counters. Further, BitSense provides a programming model to help developers easily realize sketch algorithms without dealing with the details of compression and recovery. Bit-Sense proposes an automatic approach for parameter configuration. It theoretically guarantees nearly zero error under the configuration. We have built a BitSense prototype in P4 and a software platform and integrated it with fourteen sketch solutions. Extensive experiments show that BitSense significantly reduces the memory usage of existing sketch solutions by 25%-80% while incurring little overhead and almost zero accuracy drop, outperforming five state-of-the-art optimization frameworks.