Learning Semantic Context towards Pixel-Wise Recognition

PhD Thesis Proposal Defence


Title: "Learning Semantic Context towards Pixel-Wise Recognition"

by

Mr. Mingmin ZHEN


Abstract:

Pixel-wise recognition tasks, such as semantic segmentation and salient object 
detection, aim to classify each pixel into predefined caterories. Traditional 
methods suffer from the poor disriminative ability of hand-crafted features. In 
this work, we delve into the CNN based methods to advance semantic segmentation 
and salient object dection.

For semantic segmentation, we firstly introduce a  fully dense  neural network 
with an encoder-decoder structure that we abbreviate as  FDNet, in which
  feature maps of  all the previous blocks are adaptively aggregated to 
feedforward as  input. On the one hand,  it reconstructs  the spatial 
boundaries accurately. On the other hand, it learns more efficiently  with the 
more efficient  gradient backpropagation. We then present an  joint multi-task 
learning framework for semantic segmentation and semantic boundary detection. 
The critical component in the framework is the iterative pyramid context module 
(PCM), which couples two tasks and stores the shared latent semantics to 
interact between the two tasks.  A novel loss function originated from the dual 
constraint  is designed to improve further the performance for semantic 
segmentation, which ensures the consistency between semantic mask boundary and 
boundary groundtruth.

For salient object detection, we illustrate an end-to-end differentiable 
morphalogical actve contour model, which iteratively helps to improve the 
boundary accuracy of salient object.  As it is hard to determine the salient 
object from just one view, we also propose to obtain accurate salient object 
mask from multiple views, whichs adopts feature clustering method to correlate 
features from multiple views and enforces the consistency of salient object 
from different views.


Date:			Wednesday, 11 December 2019

Time:                  	4:00pm - 6:00pm

Venue:                  Room 2132B
                         (lift 19)

Committee Members:	Prof. Long Quan (Supervisor)
 			Dr. Qifeng Chen (Chairperson)
 			Dr. Pedro Sander
 			Prof. Chiew-Lan Tai


**** ALL are Welcome ****