• Publications
  • Influence
Deep Residual Learning for Image Recognition
Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitlyExpand
  • 49,732
  • 11214
  • Open Access
Identity Mappings in Deep Residual Networks
Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors. In this paper, we analyze the propagation formulationsExpand
  • 3,832
  • 740
  • Open Access
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two aspects. First, weExpand
  • 7,930
  • 648
  • Open Access
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224<inline-formula><tex-math>$\times$ </tex-math><alternatives><inline-graphic xlink:type="simple"Expand
  • 3,503
  • 372
  • Open Access
Accelerating Very Deep Convolutional Networks for Classification and Detection
This paper aims to accelerate the test-time computation of convolutional neural networks (CNNs), especially very deep CNNs <xref ref-type="bibr" rid="ref1">[1]</xref> that have substantially impactedExpand
  • 347
  • 35
  • Open Access
Trojaning Attack on Neural Networks
With the fast spread of machine learning techniques, sharing and adopting public machine learning models become very popular. This gives attackers many new opportunities. In this paper, we propose aExpand
  • 229
  • 35
  • Open Access
Z3-str: a z3-based string solver for web application analysis
Analyzing web applications requires reasoning about strings and non-strings cohesively. Existing string solvers either ignore non-string program behavior or support limited set of string operations.Expand
  • 154
  • 20
  • Open Access
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224 × 224) input image. This requirement is "artificial" and may reduce the recognition accuracy for the images orExpand
  • 602
  • 18
AsDroid: detecting stealthy behaviors in Android applications by user interface and program behavior contradiction
Android smartphones are becoming increasingly popular. The open nature of Android allows users to install miscellaneous applications, including the malicious ones, from third-party marketplacesExpand
  • 179
  • 16
  • Open Access
ExFuse: Enhancing Feature Fusion for Semantic Segmentation
Modern semantic segmentation frameworks usually combine low-level and high-level features from pre-trained backbone convolutional models to boost performance. In this paper, we first point out that aExpand
  • 151
  • 16
  • Open Access