Underwater image enhancement based on optimally weighted histogram framework and improved Fick's law algorithm.

The quality of underwater images is often affected by light scattering and attenuation, resulting in a loss of contrast and brightness. To address this issue, this paper proposes an underwater image enhancement method: improved Fick's law algorithm-based optimally weighted histogram framework (IFLAHF). The method incorporates the bi-histogram equalization-based three plateau limits (BHE3PL) technique to enhance image contrast and details while maintaining brightness.

JFDI: Joint Feature Differentiation and Interaction for domain adaptive object detection.

In unsupervised domain adaptive object detection, learning target-specific features is pivotal in enhancing detector performance. However, previous methods mostly concentrated on aligning domain-invariant features across domains and neglected integrating the specific features. To tackle this issue, we introduce a novel feature learning method called Joint Feature Differentiation and Interaction (JFDI), which significantly boosts the adaptability of the object detector.

Multi-granularity knowledge distillation and prototype consistency regularization for class-incremental learning.

Deep neural networks (DNNs) are prone to the notorious catastrophic forgetting problem when learning new tasks incrementally. Class-incremental learning (CIL) is a promising solution to tackle the challenge and learn new classes while not forgetting old ones. Existing CIL approaches adopted stored representative exemplars or complex generative models to achieve good performance.