Learning Rich Features Research Articles

Attentive multi-granularity perception network for person search

Person search is an extremely challenging task that seeks to identify individuals through joint person detection and person re-identification from uncropped real scene images. Previous studies primarily focus on learning rich features to enhance identification. However, arbitrary feature enhancement strategies may introduce unwanted background noise. Moreover, different scenarios usually exhibit varying pedestrian appearances or even intricate occlusions, leading to inconsistent/incomplete pedestrian features in different images. In this paper, we introduce a novel Attentive Multi-granularity Perception (AMP) module seamlessly integrated into our AMPN network. This module specifically addresses appearance variations and occlusions within a person's Region of Interest (RoI). The AMP module harnesses discriminative relationship features from various local regions, significantly enhancing identification accuracy. It comprises two principal components: the Pedestrian Perception Enhancement (PPE) block and the Background Interference Suppressor (BIS). The PPE block introduces a Spatial-wise Feature Mixer and a Channel-wise Feature Mixer, which effectively capture and refine discriminative relation features. Simultaneously, the BIS operates in parallel with the PPE block, enriching the discriminative relation features and enhancing the distinctiveness between the foreground and background. Our AMP module is plug-and-play and can integrate with other person search models. Extensive experiments validate our model's merits, achieving state-of-the-art performance on CUHK-SYSU and a 4.8% mAP gain over SeqNet on PRW at a desirable speed. Our code is accessible at https://github.com/zqx951102/AMPN.

Cellular data extraction from multiplexed brain imaging data using self-supervised Dual-loss Adaptive Masked Autoencoder

Reliable large-scale cell detection and segmentation is the fundamental first step to understanding biological processes in the brain. The ability to phenotype cells at scale can accelerate preclinical drug evaluation and system-level brain histology studies. The impressive advances in deep learning offer a practical solution to cell image detection and segmentation. Unfortunately, categorizing cells and delineating their boundaries for training deep networks is an expensive process that requires skilled biologists. This paper presents a novel self-supervised Dual-Loss Adaptive Masked Autoencoder (DAMA) for learning rich features from multiplexed immunofluorescence brain images. DAMA’s objective function minimizes the conditional entropy in pixel-level reconstruction and feature-level regression. Unlike existing self-supervised learning methods based on a random image masking strategy, DAMA employs a novel adaptive mask sampling strategy to maximize mutual information and effectively learn brain cell data. To the best of our knowledge, this is the first effort to develop a self-supervised learning method for multiplexed immunofluorescence brain images. Our extensive experiments demonstrate that DAMA features enable superior cell detection, segmentation, and classification performance without requiring many annotations. In addition, to examine the generalizability of DAMA, we also experimented on TissueNet, a multiplexed imaging dataset comprised of two-channel fluorescence images from six distinct tissue types, captured using six different imaging platforms. Our code is publicly available at https://github.com/hula-ai/DAMA.

Learning rich features for gait recognition by integrating skeletons and silhouettes

Learning rich features for gait recognition by integrating skeletons and silhouettes

Learning rich features with hybrid loss for brain tumor segmentation

BackgroundAccurately segment the tumor region of MRI images is important for brain tumor diagnosis and radiotherapy planning. At present, manual segmentation is wildly adopted in clinical and there is a strong need for an automatic and objective system to alleviate the workload of radiologists.MethodsWe propose a parallel multi-scale feature fusing architecture to generate rich feature representation for accurate brain tumor segmentation. It comprises two parts: (1) Feature Extraction Network (FEN) for brain tumor feature extraction at different levels and (2) Multi-scale Feature Fusing Network (MSFFN) for merge all different scale features in a parallel manner. In addition, we use two hybrid loss functions to optimize the proposed network for the class imbalance issue.ResultsWe validate our method on BRATS 2015, with 0.86, 0.73 and 0.61 in Dice for the three tumor regions (complete, core and enhancing), and the model parameter size is only 6.3 MB. Without any post-processing operations, our method still outperforms published state-of-the-arts methods on the segmentation results of complete tumor regions and obtains competitive performance in another two regions.ConclusionsThe proposed parallel structure can effectively fuse multi-level features to generate rich feature representation for high-resolution results. Moreover, the hybrid loss functions can alleviate the class imbalance issue and guide the training process. The proposed method can be used in other medical segmentation tasks.

A Hybrid Deep Network Framework for Android Malware Detection

Android is a growing target for malicious software (malware) because of its popularity and functionality. Malware poses a serious threat to users’ privacy, money, equipment and file integrity. A series of data-driven malware detection methods were proposed. However, there exist two key challenges for these methods: (1) how to learn effective feature representation from raw data; (2) how to reduce the dependence on the prior knowledge or human labors in feature learning. Inspired by the success of deep learning methods in the feature representation learning community, we propose a malware detection framework which starts with learning rich-features by a novel unsupervised feature learning algorithm Merged Sparse Auto-Encoder (MSAE). In order to extract more compact and discriminative feature from the rich-features to further boost the malware detection capability, a hybrid deep network learning algorithm Stacked Hybrid Learning MSAE and SDAE (SHLMD) is established by further incorporating a classical deep learning method Stacked Denoising Auto-encoders (SDAE). After that, we feed the feature learned by MSAE and SHLMD respectively to classification algorithms, e.g., Support Vector Machine (SVM) or K-NearestNeighbor (KNN), to train a malware detection model. Evaluation results on two real-world datasets demonstrate that SHLMD achieves 94.46 and 90.57 percent accuracy respectively, which outperforms the classical unsupervised feature representation learning Sparse Auto-encoder (SAE). MSAE performs similarly to SAE. SHLMD can further improve the performance of MSAE and the supervised fine-tuned method SDAE. Besides, we compare the performance of our methods with that of state-of-the-art detection approaches, including classical deep-learning-based methods. Extensive experiments show that our proposed methods are effective enough to detect Android malware.

AsNet: Asymmetrical Network for Learning Rich Features in Person Re-Identification

Learning part-based features with multiple branches has been proven as an effective way to deliver high performance person re-identification. Existing works mostly exploit extra constraints on different branches to ensure the diversity of extracted features, which may lead to the increased complexity in network architecture and the difficulty for training. In this letter, we propose a quite simple multi-branch structure consisting of a global branch as well as a part branch in an asymmetrical way. We empirically demonstrate that such simple architecture can provide surprisingly high performance without imposing any extra constraint. On top of this, we further prompt the performance with a lightweight implementation of attention module. Extensive experimental results prove that the proposed method, termed Asymmetrical Network (AsNet), outperforms state-of-the-art methods with obvious margin on standard benchmark datasets such as Market1501, DukeMTMC, CUHK03. We believe that AsNet can serve as a strong baseline for related research and the source code is publicly available at https://github.com/www0wwwjs1/asnet.git .

Cross-Project Transfer Representation Learning for Vulnerable Function Discovery

Machine learning is now widely used to detect security vulnerabilities in the software, even before the software is released. But its potential is often severely compromised at the early stage of a software project when we face a shortage of high-quality training data and have to rely on overly generic hand-crafted features. This paper addresses this cold-start problem of machine learning, by learning rich features that generalize across similar projects. To reach an optimal balance between feature-richness and generalizability, we devise a data-driven method including the following innovative ideas. First, the code semantics are revealed through serialized abstract syntax trees (ASTs), with tokens encoded by Continuous Bag-of-Words neural embeddings. Next, the serialized ASTs are fed to a sequential deep learning classifier (Bi-LSTM) to obtain a representation indicative of software vulnerability. Finally, the neural representation obtained from existing software projects is then transferred to the new project to enable early vulnerability detection even with a small set of training labels. To validate this vulnerability detection approach, we manually labeled 457 vulnerable functions and collected 30 000+ nonvulnerable functions from six open-source projects. The empirical results confirmed that the trained model is capable of generating representations that are indicative of program vulnerability and is adaptable across multiple projects. Compared with the traditional code metrics, our transfer-learned representations are more effective for predicting vulnerable functions, both within a project and across multiple projects.

Learning rich features from objectness estimation for human lying-pose detection

Lying-pose human detection is an active research field of computer vision in recent years. It has a good theoretical significance and furthermore many applications, such as victim detection or home...