[cs-talks] PhD Thesis Defense, Jianming Zhang, Thursday August 11, 2016 at 2:00 Hariri Institute for Computing Seminar Room MCS 180
jenn4 at bu.edu
Thu Aug 11 12:13:55 EDT 2016
PhD Thesis Defense
Visual Saliency Computation for Image Analysis
Thursday, Aug. 11, 2pm.
Hariri Seminar Room MCS 180, 111 Cummington Mall
Visual saliency computation is about detecting and understanding salient regions and elements in a visual scene. Algorithms for visual saliency computation can give clues to where people will look in images, what objects are visually prominent in an image (foreground), etc. Such algorithms could be useful in a wide range of applications in computer vision and graphics. In this thesis, we study the following visual saliency computation problems. 1) Eye Fixation Prediction. Eye fixation prediction aims to predict where people look when they free-view static images. For this problem, we propose a Boolean Map Saliency (BMS) model which leverages the global surroundedness cue using a Boolean map representation. We draw a theoretic connection between BMS and the Minimum Barrier Distance (MBD) transform to provide insight into our algorithm. Experiment results show that BMS compares favorably with state-of-the-art methods on seven benchmark datasets. 2) Salient Region Detection. Salient region detection entails computing a saliency map that highlights the regions of dominant objects in a scene. We propose a salient region detection method based on the Minimum Barrier Distance (MBD) transform. We present a fast approximate MBD transform algorithm with an error bound analysis. Powered by this fast MBD transform algorithm, our method can run at about 80 FPS and achieve state-of-the-art performance on four benchmark datasets. 3) Salient Object Detection. Salient object detection targets at localizing each salient object instance in a image. We propose a method using a Convolutional Neural Network (CNN) model for proposal generation and a novel subset optimization formulation for bounding box filtering. In experiments, our subset optimization formulation consistently outperforms heuristic bounding box filtering baselines, such as Non-maximum Suppression, and our method substantially outperforms previous methods on three challenging datasets. 4) Salient Object Subitizing. We propose a new visual saliency computation task, called Salient Object Subitizing, which is which is to predict the existence and the number of salient objects in an image using holistic cues. To this end, we present a image dataset of about 14K everyday images which are annotated using an online crowdsourcing marketplace. We show that an end-to-end trained CNN subitizing model can achieve promising performance without requiring any localization process. A method is proposed to further improve the training of the CNN subitizing model by leveraging synthetic images. 5) Top-down Saliency Detection. Unlike the aforementioned tasks, top-down saliency detection entails generating task-specific saliency maps. We propose a weakly supervised top-down saliency detection approach by modeling the top-down attention of a CNN image classifier. We propose Excitation Backprop and the concept of contrastive attention to generate highly discriminative top-down saliency maps. Our top-down saliency detection method achieves superior performance in weakly supervised localization tasks on challenging datasets. The usefulness of our method is further validated in the text-to-region association task, where our method provides state-of-the-art performance using only weakly labeled web images for training.
First reader: Prof. Stan Sclaroff
Second reader: Prof. Margrit Betke
Third reader: Prof. Lorenzo Torresani (Dartmouth College)
Committee chair: Prof. Lorenzo Orecchia
Additional committee member: Prof. Kate Saenko
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the cs-talks