1 November 2024 in IEEE Transactions on Geoscience and Remote Sensing
Recently, infrared small target detection (ISTD) has made significant progress, thanks to the development of basic models. Specifically, the models combining CNNs with transformers can successfully extract both local and global features. However, the disadvantage of the transformer is also inherited, i.e., the quadratic computational complexity to sequence length. Inspired by the recent basic model with linear complexity for long-distance modeling, Mamba, we explore the potential of this state space model for ISTD task in terms of effectiveness and efficiency in the paper. However, directly applying Mamba achieves suboptimal performances due to the insufficient harnessing of local features, which are imperative for detecting small targets. Instead, we tailor a nested structure, Mamba-in-Mamba (MiM-ISTD), for efficient ISTD. It consists of Outer and Inner Mamba blocks to adeptly capture both global and local features. Specifically, we treat the local patches as "visual sentences" and use the Outer Mamba to explore the global information. We then decompose each visual sentence into sub-patches as "visual words" and use the Inner Mamba to further explore the local information among words in the visual sentence with negligible computational costs. By aggregating the visual word and visual sentence features, our MiM-ISTD can effectively explore both global and local information. Experiments on NUAA-SIRST and IRSTD-1k show the superior accuracy and efficiency of our method. Specifically, MiM-ISTD is 8× faster than the SOTA method and reduces GPU memory usage by 62.2% when testing on 2048 × 2048 images, overcoming the computation and memory constraints on high-resolution infrared images.
29 April 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional semantic image synthesis in T. Park et al. 2019 which modulates the normalized activation with spatially-varying transformations learned from semantic layouts, to prevent the semantic information from being washed away. Despite its impressive performance, a more thorough understanding of the advantages inside the box is still highly demanded to help reduce the significant computation and parameter overhead introduced by this novel structure. In this paper, from a return-on-investment point of view, we conduct an in-depth analysis of the effectiveness of this spatially-adaptive normalization and observe that its modulation parameters benefit more from semantic-awareness rather than spatial-adaptiveness, especially for high-resolution input masks. Inspired by this observation, we propose class-adaptive normalization (CLADE), a lightweight but equally-effective variant that is only adaptive to semantic class. In order to further improve spatial-adaptiveness, we introduce intra-class positional map encoding calculated from semantic layouts to modulate the normalization parameters of CLADE and propose a truly spatially-adaptive variant of CLADE, namely CLADE-ICPE. Through extensive experiments on multiple challenging datasets, we demonstrate that the proposed CLADE can be generalized to different SPADE-based methods while achieving comparable generation quality compared to SPADE, but it is much more efficient with fewer extra parameters and lower computational cost. The code and pretrained models are available at https://github.com/tzt101/CLADE.git .
12 October 2021 in IEEE Transactions on Biometrics, Behavior, and Identity Science
Over the past several years, to solve the problem of malicious abuse of facial manipulation technology, face manipulation detection has obtained considerable attention. Although existing works achieved impressive performance on a hold-out test set, their methods suffered a significant performance drop on data from a different distribution than the training set used. In this paper, we conduct an in-depth analysis on existing typical models about poor generalization capability and propose a novel method for face manipulation detection, which can alleviate overfitting and improve the generalization ability by learning forgery region aware and ID-independent features. Specifically, a forgery region guided self-attention module (FR) is introduced to make the model focus on the forgery region and a landmark guided dropout module (LM) is designed to randomly remove features of structured informative regions for destroying identity features. These two regularization modules are then added to the basic classification network, e.g., Xception. With the help of the joint learning framework, both forgery region-aware and ID-independent features are learned for face manipulation detection with better generalization ability. Extensive experiments demonstrate that the proposed method can not only outperform competing state-of-the-art methods on the FaceForensics++ dataset but also achieve superior generalization performance on the Celeb-DF dataset.
17 April 2025 in IEEE Transactions on Medical Imaging
Medical image segmentation has made significant strides with the development of basic models. Specifically, models that combine CNNs with transformers can successfully extract both local and global features. However, these models inherit the transformer’s quadratic computational complexity, limiting their efficiency. Inspired by the recent Receptance Weighted Key Value (RWKV) model, which achieves linear complexity for long-distance modeling, we explore its potential for medical image segmentation. While directly applying vision-RWKV yields suboptimal results due to insufficient local feature exploration and disrupted spatial continuity, we propose a novel nested structure, Zigzag RWKV-in-RWKV (Zig-RiR), to address these issues. It consists of Outer and Inner RWKV blocks to adeptly capture both global and local features without disrupting spatial continuity. We treat local patches as ”visual sentences” and use the Outer Zig-RWKV to explore global information. Then, we decompose each sentence into subpatches (”visual words”) and use the Inner Zig-RWKV to further explore local information among words, at negligible computational cost. We also introduce a Zigzag-WKV attention mechanism to ensure spatial continuity during token scanning. By aggregating visual word and sentence features, our Zig-RiR can effectively explore both global and local information while preserving spatial continuity. Experiments on four medical image segmentation datasets of both 2D and 3D modalities demonstrate the superior accuracy and efficiency of our method, outperforming the state-of-the-art method 14.4 times in speed and reducing GPU memory usage by 89.5% when testing on 1024 × 1024 high-resolution medical images. Our code is available at https://github.com/txchen-USTC/Zig-RiR.
4 February 2020 in IEEE Transactions on Circuits and Systems for Video Technology
Many of the recent methods for semi-supervised video object segmentation are still far from being applicable for real time applications due to their slow inference speed. Therefore, we explore a propagation based segmentation method in compressed domain to accelerate inference speed in this paper. In particular, we only extract the features of I-frames by traditional deep convolutional neural network and produce the features of P-frames through information flow propagation. In the process of feature propagation, we propose two effective components to enhance the representation ability of simply warped features in terms of appearance and location. Specifically, we propose a residual supplement module to supplement appearance information which is lost in direct warping and a spatial attention module that can mine extra spatial saliency to provide the location information of the specified object. Besides, we propose a metric based decoder module which consists of a feature match module and a multi-level refinement module to transform information from semantic representation to shape segmentation mask. Extensive experiments on several video datasets demonstrate that the proposed method can achieve comparable accuracy while much faster inference speed when compared to the state-of-the-art algorithms.