Silong Peng

Popular rotated detection methods usually use five parameters (coordinates of the central point, width, height, and rotation angle) or eight parameters (coordinates of four vertices) to describe the rotated bounding box and l1 loss as the loss function. In this paper, we argue that the aforementioned integration can cause training instability and performance degeneration. The main reason is the discontinuity of loss which is caused by the contradiction between the definition of the rotated bounding box and the loss function. We refer to the above issues as rotation sensitivity error (RSE) and propose a modulated rotation loss to dismiss the discontinuity of loss. The modulated rotation loss can achieve consistent improvement on the five parameter methods and the eight parameter methods. Experimental results using one stage and two stages detectors demonstrate the effectiveness of our loss. The integrated network achieves competitive performances on several benchmarks including DOTA and UCAS AOD. The code is available at https://github.com/yangxue0827/RotationDetection.

Empirical mode decomposition (EMD) is an adaptive and data-driven approach for analyzing multicomponent nonlinear and nonstationary signals. The stop criterion, envelope technique, and mode-mixing problem are the most important topics that need to be addressed in order to improve the EMD algorithm. In this paper, we study the envelope technique and the mode-mixing problem caused by separating multicomponent AM-FM signals with the EMD algorithm. We present a new necessary condition on the envelope that questions the current assumption that the envelope passes through the extreme points of an intrinsic mode function (IMF). Then, we present a solution to the mode-mixing problem that occurs when multicomponent AM-FM signals are separated. We experiment on several signals, including simulated signals and real-life signals, to demonstrate the efficacy of the proposed method in resolving the mode-mixing problem.

With the springing up of face synthesis techniques, it is prominent in need to develop powerful face forgery detection methods due to security concerns. Some existing methods attempt to employ auxiliary frequency-aware information combined with CNN backbones to discover the forged clues. Due to the inadequate information interaction with image content, the extracted frequency features are thus spatially irrelavant, struggling to generalize well on increasingly realistic counterfeit types. To address this issue, we propose a Spatial-Frequency Dynamic Graph method to exploit the relation-aware features in spatial and frequency domains via dynamic graph learning. To this end, we introduce three well-designed components: 1) Content-guided Adaptive Frequency Extraction module to mine the content-adaptive forged frequency clues. 2) Multiple Domains Attention Map Learning module to enrich the spatial-frequency contextual features with multiscale attention maps. 3) Dynamic Graph Spatial-Frequency Feature Fusion Network to explore the high-order relation of spatial and frequency features. Extensive experiments on several benchmark show that our proposed method sustainedly exceeds the state-of-the-arts by a considerable margin.

In this paper we propose an image super-resolution algorithm using wavelet-domain hidden Markov tree (HMT) model. Wavelet-domain HMT models the dependencies of multiscale wavelet coefficients through the state probabilities of wavelet coefficients, whose distribution densities can be approximated by the Gaussian mixture. Because wavelet-domain HMT accurately characterizes the statistics of real-world images, we reasonably specify it as the prior distribution and then formulate the image super-resolution problem as a constrained optimization problem. And the cycle-spinning technique is used to suppress the artifacts that may exist in the reconstructed high-resolution images. Quantitative error analyses are provided and several experimental images are shown for subjective assessment.