G2

GC

Verified User in Computer Software

Mid-Market (51-1000 emp.)

7/23/2018

"An extensive computer vision library"

4.5/5

What do you like best about VLFeat?

Many good baselines for popular computer vision techniques such as SIFT and HOG, along with a good SVM implementation. Also good documentation. Review collected by and hosted on G2.com.

What do you dislike about VLFeat?

Doesn't support more recent deep learning techniques (but see Matconvnet). Requires Matlab to use the high level APIs (or Octave, but this is less well supported). Review collected by and hosted on G2.com.

Recommendations to others considering VLFeat:

Good for baselines and reference implementations of popular computer vision methods. Review collected by and hosted on G2.com.

What problems is VLFeat solving and how is that benefiting you?

Extracting SIFT and HOG features as an object recognition baseline. Thin plate spline warps for data augmentation when training neural networks. Review collected by and hosted on G2.com.