SwePub
Sök i LIBRIS databas

  Extended search

onr:"swepub:oai:DiVA.org:ltu-94847"
 

Search: onr:"swepub:oai:DiVA.org:ltu-94847" > Depth Contrast: Sel...

  • 1 of 1
  • Previous record
  • Next record
  •    To hitlist

Depth Contrast: Self-Supervised Pretraining on 3DPM Images for Mining Material Classification

Chhipa, Prakash Chandra (author)
Luleå tekniska universitet,EISLAB
Upadhyay, Richa (author)
Luleå tekniska universitet,EISLAB
Saini, Rajkumar, Dr. 1988- (author)
Luleå tekniska universitet,EISLAB
show more...
Lindqvist, Lars (author)
Optimation Advanced Measurements AB, Luleå, Sweden
Nordenskjold, Richard (author)
Optimation Advanced Measurements AB, Luleå, Sweden
Uchida, Seiichi (author)
Human Interface Laboratory, Kyushu University, Fukuoka, Japan
Liwicki, Marcus (author)
Luleå tekniska universitet,EISLAB
show less...
 (creator_code:org_t)
English.
  • Other publication (other academic/artistic)
Abstract Subject headings
Close  
  • This work presents a novel self-supervised representation learning method to learn efficient representations without labels on images from a 3DPM sensor (3-Dimensional Particle Measurement; estimates the particle size distribution of material) utilizing RGB images and depth maps of mining material on the conveyor belt. Human annotations for material categories on sensor-generated data are scarce and cost-intensive. Currently, representation learning without human annotations remains unexplored for mining materials and does not leverage on utilization of sensor-generated data. The proposed method, Depth Contrast, enables self-supervised learning of representations without labels on the 3DPM dataset by exploiting depth maps and inductive transfer. The proposed method outperforms material classification over ImageNet transfer learning performance in fully supervised learning settings and achieves an F1 score of 0.73. Further, The proposed method yields an F1 score of 0.65 with an 11% improvement over ImageNet transfer learning performance in a semi-supervised setting when only 20% of labels are used in fine-tuning. Finally, the Proposed method showcases improved performance generalization on linear evaluation. The implementation of proposed method is available on GitHub. 

Subject headings

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Sciences (hsv//eng)

Keyword

Maskininlärning
Machine Learning

Publication and Content Type

vet (subject category)
ovr (subject category)

To the university's database

  • 1 of 1
  • Previous record
  • Next record
  •    To hitlist

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Close

Copy and save the link in order to return to this view