LAMP

The Learning and Machine Perception (LAMP) team at the Computer Vision Center conducts fundamental research and technology transfer in the field of machine learning for semantic understanding of visual data. The group works with a wide variety of visual data sources: from multispectral, medical imagery and consumer camera images, to live webcam streams and video data. The returning objective is the design of efficient and accurate algorithms for the automatic extraction of semantic information from visual media.

See here current open positions.

Riccardo’s paper >RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning on continual learning of captioning systems, and Yaxing’s paper on transfer learning for image-to-image systems:DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs have been accepted !

Four CVPR papers have been accepted:

• MineGAN: effective knowledge transfer from GANs to target domains with few images,
• Orderless Recurrent Models for Multi-label Classification,
• Semantic Drift Compensation for Class-Incremental Learning,
• Semi-supervised Learning for Few-shot Image-to-Image Translation.

and one workshop paper:

• Generative Feature Replay For Class-Incremental Learning,

Lichao’s paper on visual tracking Learning the Model Update for Siamese Trackers and Hamed’s paper on active learning Active Learning for Deep Detection Neural Networks (github) have been accepted for ICCV. Also, David Berga has a paper with Xavier Otazu on saliency detection: SID4VAM: A Benchmark Dataset With Synthetic Images for Visual Attention Modeling .

Two NIPS papers got accepted. One work on ‘Image-to-image translation for cross-domain disentanglement’ (pdf) and one titled ‘Memory Replay GANs: Learning to Generate New Categories without Forgetting’ (pdf + blog + video).