Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning

Abstract

We develop methods for detector learning which exploit joint training over both weak and strong labels and which transfer learned perceptual representations from strongly-labeled auxiliary tasks. Previous methods for weak-label learning often learn detector models independently using latent variable optimization, but fail to share deep representation knowledge across classes and usually require strong initialization. Other previous methods transfer deep representations from domains with strong labels to those with only weak labels, but do not optimize over individual latent boxes, and thus may miss specific salient structures for a particular category. We propose a model that subsumes these previous approaches, and simultaneously trains a representation and detectors for categories with either weak or strong labels present. We provide a novel formulation of a joint multiple instance learning method that includes examples from classification-style data when available, and also performs domain transfer learning to improve the underlying detector representation. Our model outperforms known methods on ImageNet-200 detection with weak labels.

References in corpus (2)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Frustratingly Easy Domain Adaptation

Cited by in corpus (5)

• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Fully Convolutional Multi-Class Multiple Instance Learning
• Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption
• Weakly- and Semi-Supervised Object Detection with Expectation-Maximization Algorithm
• Constrained Convolutional Neural Networks for Weakly Supervised Segmentation