Abstract
We introduce a text-based image feature and demon- strate that it consistently improves performance on hard object classification problems. The feature is built using an auxiliary dataset of images annotated with tags, down- loaded from the internet. We do not inspect or correct the tags and expect that they are noisy. We obtain the text fea- ture of an unannotated image from the tags of its k-nearest neighbors in this auxiliary collection. A visual classifier presented with an object viewed un- der novel circumstances (say, a new viewing direction) must rely on its visual examples. Our text feature may not change, because the auxiliary dataset likely contains a similar pic- ture. While the tags associated with images are noisy, they are more stable when appearance changes. We test the performance of this feature using PAS- CAL VOC 2006 and 2007 datasets. Our feature performs well, consistently improves the performance of visual ob- ject classifiers, and is particularly effective when the train- ing dataset is small.
| Original language | English (US) |
|---|---|
| Title of host publication | 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009 |
| Publisher | IEEE Computer Society |
| Pages | 1367-1374 |
| Number of pages | 8 |
| ISBN (Print) | 9781424439935 |
| DOIs | |
| State | Published - Jan 1 2009 |
| Event | 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Miami, FL, United States Duration: Jun 20 2009 → Jun 25 2009 |
Publication series
| Name | 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009 |
|---|---|
| Volume | 2009 IEEE Computer Society Conference on Computer Vision and ... |
Other
| Other | 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
|---|---|
| Country | United States |
| City | Miami, FL |
| Period | 6/20/09 → 6/25/09 |
Fingerprint
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Biomedical Engineering
Cite this
Building text features for object image classification. / Wang, Gang; Hoiem, Derek W; Forsyth, David Alexander.
2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. IEEE Computer Society, 2009. p. 1367-1374 5206816 (2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009; Vol. 2009 IEEE Computer Society Conference on Computer Vision and ...).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Building text features for object image classification
AU - Wang, Gang
AU - Hoiem, Derek W
AU - Forsyth, David Alexander
PY - 2009/1/1
Y1 - 2009/1/1
N2 - We introduce a text-based image feature and demon- strate that it consistently improves performance on hard object classification problems. The feature is built using an auxiliary dataset of images annotated with tags, down- loaded from the internet. We do not inspect or correct the tags and expect that they are noisy. We obtain the text fea- ture of an unannotated image from the tags of its k-nearest neighbors in this auxiliary collection. A visual classifier presented with an object viewed un- der novel circumstances (say, a new viewing direction) must rely on its visual examples. Our text feature may not change, because the auxiliary dataset likely contains a similar pic- ture. While the tags associated with images are noisy, they are more stable when appearance changes. We test the performance of this feature using PAS- CAL VOC 2006 and 2007 datasets. Our feature performs well, consistently improves the performance of visual ob- ject classifiers, and is particularly effective when the train- ing dataset is small.
AB - We introduce a text-based image feature and demon- strate that it consistently improves performance on hard object classification problems. The feature is built using an auxiliary dataset of images annotated with tags, down- loaded from the internet. We do not inspect or correct the tags and expect that they are noisy. We obtain the text fea- ture of an unannotated image from the tags of its k-nearest neighbors in this auxiliary collection. A visual classifier presented with an object viewed un- der novel circumstances (say, a new viewing direction) must rely on its visual examples. Our text feature may not change, because the auxiliary dataset likely contains a similar pic- ture. While the tags associated with images are noisy, they are more stable when appearance changes. We test the performance of this feature using PAS- CAL VOC 2006 and 2007 datasets. Our feature performs well, consistently improves the performance of visual ob- ject classifiers, and is particularly effective when the train- ing dataset is small.
UR - http://www.scopus.com/inward/record.url?scp=70450207253&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70450207253&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2009.5206816
DO - 10.1109/CVPRW.2009.5206816
M3 - Conference contribution
AN - SCOPUS:70450207253
SN - 9781424439935
T3 - 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
SP - 1367
EP - 1374
BT - 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
PB - IEEE Computer Society
ER -