A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
arXiv:1704.03414
Abstract
How do we learn an object detector that is invariant to occlusions and deformations? Our current solution is to use a data-driven strategy -- collect large-scale datasets which have object instances under different conditions. The hope is that the final classifier can use these examples to learn invariances. But is it really possible to see all the occlusions in a dataset? We argue that like categories, occlusions and object deformations also follow a long-tail. Some occlusions and deformations are so rare that they hardly happen; yet we want to learn a model invariant to such occurrences. In this paper, we propose an alternative solution. We propose to learn an adversarial network that generates examples with occlusions and deformations. The goal of the adversary is to generate examples that are difficult for the object detector to classify. In our framework both the original detector and adversary are learned in a joint manner. Our experimental results indicate a 2.3% mAP boost on VOC07 and a 2.6% mAP boost on VOC2012 object detection challenge compared to the Fast-RCNN pipeline. We also release the code for this paper.
arXiv commentCVPR 2017 Camera Ready
References in corpus (18)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- Improved Techniques for Training GANs
- OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
- Learning to Segment Object Candidates
- DenseBox: Unifying Landmark Localization with End to End Object Detection
- Aggregated Residual Transformations for Deep Neural Networks
- Action Recognition using Visual Attention
- Beyond Skip Connections: Top-Down Modulation for Object Detection
- Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
- Unsupervised Learning of Visual Representations using Videos
- Online Batch Selection for Faster Training of Neural Networks
- Speed/accuracy trade-offs for modern convolutional object detectors
- Fracking Deep Convolutional Image Descriptors
- Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
Cited by in corpus (6)
- An Introduction to Image Synthesis with Generative Adversarial Nets
- ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing
- Conditional Adversarial Network for Semantic Segmentation of Brain Tumor
- 3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks
- Delving Deep into Liver Focal Lesion Detection: A Preliminary Study
- Unsupervised data augmentation for object detection