PLEASD
PLEASD: A Matlab Toolbox for Structured Learning
view repo
Structured learning is appropriate when predicting structured outputs such as trees, graphs, or sequences. Most prior work requires the training set to consist of complete trees, graphs or sequences. Specifying such detailed ground truth can be tedious or infeasible for large outputs. Our main contribution is a large margin formulation that makes structured learning from only partially annotated data possible. The resulting optimization problem is non-convex, yet can be efficiently solve by concave-convex procedure (CCCP) with novel speedup strategies. We apply our method to a challenging tracking-by-assignment problem of a variable number of divisible objects. On this benchmark, using only 25 a full annotation we achieve a performance comparable to a model learned with a full annotation. Finally, we offer a unifying perspective of previous work using the hinge, ramp, or max loss for structured learning, followed by an empirical comparison on their practical performance.
READ FULL TEXT
For many structured learning tasks, the data annotation process is compl...
read it
Learning structured outputs with general structures is computationally
c...
read it
The standard margin-based structured prediction commonly uses a maximum ...
read it
Partial label learning deals with the problem where each training instan...
read it
We present a fully-supervized method for learning to segment data struct...
read it
Data deletion algorithms aim to remove the influence of deleted data poi...
read it
We propose an effective optimization algorithm for a general hierarchica...
read it
Comments
There are no comments yet.