Attributes Make Sense on Segmented Objects

详细信息    查看全文

• 作者：Zhenyang Li (19)
  Efstratios Gavves (19)
  Thomas Mensink (19)
  Cees G. M. Snoek (19)
  
• 关键词：attributes ; segmentation ; zero ; shot classification
• 刊名：Lecture Notes in Computer Science
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：8694
• 期：1
• 页码：350-365
• 全文大小：1,130 KB
• 参考文献：1. Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label-embedding for attribute-based classification. In: CVPR (2013)
  2. Alexe, B., Deselaers, T., Ferrari, V.: Measuring the objectness of image windows. TPAMI (2012)
  3. Arbelaez, P., Hariharan, B., Gu, C., Gupta, S., Bourdev, L., Malik, J.: Semantic segmentation using regions and parts. In: CVPR (2012)
  4. Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: From contours to regions: An empirical evaluation. In: CVPR (2009)
  5. Blaschko, M.B., Lampert, C.H.: Learning to localize objects with structured output regression. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol.聽5302, pp. 2鈥?5. Springer, Heidelberg (2008) CrossRef
  6. Bourdev, L., Maji, S., Malik, J.: Describing people: A poselet-based approach to attribute classification. In: ICCV (2011)
  7. Branson, S., Wah, C., Schroff, F., Babenko, B., Welinder, P., Perona, P., Belongie, S.: Visual recognition with humans in the loop. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol.聽6314, pp. 438鈥?51. Springer, Heidelberg (2010) CrossRef
  8. Carreira, J., Caseiro, R., Batista, J., Sminchisescu, C.: Semantic segmentation with second-order pooling. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol.聽7578, pp. 430鈥?43. Springer, Heidelberg (2012) CrossRef
  9. Carreira, J., Li, F., Sminchisescu, C.: Object recognition by sequential figure-ground ranking. IJCV (2012)
  10. Carreira, J., Sminchisescu, C.: CPMC: Automatic object segmentation using constrained parametric min-cuts. TPAMI (2012)
  11. Chai, Y., Lempitsky, V., Zisserman, A.: BiCoS: A bi-level co-segmentation method for image classification. In: ICCV (2011)
  12. Chai, Y., Rahtu, E., Lempitsky, V., Van Gool, L., Zisserman, A.: TriCoS: A tri-level class-discriminative co-segmentation method for image classification. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol.聽7572, pp. 794鈥?07. Springer, Heidelberg (2012) CrossRef
  13. Deng, J., Krause, J., Fei-Fei, L.: Fine-grained crowdsourcing for fine-grained recognition. In: CVPR (2013)
  14. Duan, K., Parikh, D., Crandall, D., Grauman, K.: Discovering localized attributes for fine-grained recognition. In: CVPR (2012)
  15. Endres, I., Hoiem, D.: Category-independent object proposals with diverse ranking. TPAMI (2014)
  16. Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. IJCV (2010)
  17. Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: CVPR (2009)
  18. Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. TPAMI (2010)
  19. Ferrari, V., Zisserman, A.: Learning visual attributes. In: NIPS (2007)
  20. Gavves, E., Fernando, B., Snoek, C., Smeulders, A., Tuytelaars, T.: Fine-grained categorization by alignments. In: ICCV (2013)
  21. Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)
  22. Kolmogorov, V., Zabin, R.: What energy functions can be minimized via graph cuts? TPAMI (2004)
  23. Kovashka, A., Grauman, K.: Attribute adaptation for personalized image search. In: ICCV (2013)
  24. Lampert, C., Blaschko, M., Hofmann, T.: Efficient subwindow search: A branch and bound framework for object localization. TPAMI (2009)
  25. Lampert, C., Nickisch, H., Harmeling, S.: Attribute-based transfer learning for object categorization with zero/one training example. TPAMI (2013)
  26. Li, Z., Gavves, E., van de Sande, K., Snoek, C., Smeulders, A.: Codemaps segment, classify and search objects locally. In: ICCV (2013)
  27. Manen, S., Guillaumin, M., Van Gool, L.: Prime object proposals with randomized prim鈥檚 algorithm. In: ICCV (2013)
  28. Parikh, D., Grauman, K.: Relative attributes. In: ICCV (2011)
  29. S谩nchez, J., Perronnin, F., Mensink, T., Verbeek, J.: Image classification with the fisher vector: Theory and practice. IJCV (2013)
  30. van de Sande, K., Gevers, T., Snoek, C.: Evaluating color descriptors for object and scene recognition. TPAMI (2010)
  31. Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables (2005)
  32. Uijlings, J., van de Sande, K., Gevers, T., Smeulders, A.: Selective search for object recognition. IJCV (2013)
  33. Uijlings, J., Smeulders, A., Scha, R.: The visual extent of an object. IJCV (2012)
  34. Usunier, N., Buffoni, D., Gallinar, P.: Ranking with ordered weighted pairwise classification. In: ICML (2009)
  35. Vijayanarasimhan, S., Grauman, K.: Efficient region search for object detection. In: CVPR (2011)
  36. Wah, C., Branson, S., Perona, P., Belongie, S.: Multiclass recognition and part localization with humans in the loop. In: ICCV (2011)
  37. Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Tech. rep. (2011)
  38. Wang, J., Markert, K., Everingham, M.: Learning models for object recognition from natural language descriptions. In: BMVC (2009)
  39. Weston, J., Bengio, S., Usunier, N.: WSABIE: Scaling up to large vocabulary image annotation. In: IJCAI (2011)
  40. Zhu, S., Angelova, A.: Efficient object detection and segmentation for fine-grained recognition. In: CVPR (2013)
  
• 作者单位：Zhenyang Li (19)
  Efstratios Gavves (19)
  Thomas Mensink (19)
  Cees G. M. Snoek (19)
  
  19. ISLA, Informatics Institute, University of Amsterdam, The Netherlands
  
• ISSN：1611-3349

文摘

In this paper we aim for object classification and segmentation by attributes. Where existing work considers attributes either for the global image or for the parts of the object, we propose, as our first novelty, to learn and extract attributes on segments containing the entire object. Object-level attributes suffer less from accidental content around the object and accidental image conditions such as partial occlusions, scale changes and viewpoint changes. As our second novelty, we propose joint learning for simultaneous object classification and segment proposal ranking, solely on the basis of attributes. This naturally brings us to our third novelty: object-level attributes for zero-shot, where we use attribute descriptions of unseen classes for localizing their instances in new images and classifying them accordingly. Results on the Caltech UCSD Birds, Leeds Butterflies, and an a-Pascal subset demonstrate that i) extracting attributes on oracle object-level brings substantial benefits ii) our joint learning model leads to accurate attribute-based classification and segmentation, approaching the oracle results and iii) object-level attributes also allow for zero-shot classification and segmentation.We conclude that attributes make sense on segmented objects.