A zoo and garden of active basis models

Learning with unknown rotations plus unknown locations and scales

In the following experiments, we allow the change of orientations of the objects, sometimes also the right-left flips, in addition to the change of locations and scales as in experiment 5. The training images are cherry picked from internet. We are rather easy on the code in terms of scale change, mainly for the consideration of speed. We tuned two parameters: One is the number of basis elements in the template. The other is the common resize factor applied to all the training images. Other parameters are kept unchanged.

The learning algorithm is initialized from learning a template from the first training image. In a more thorough implementation, we can initialize the algorithm multiple times from cropped image patches such as in Experiment 5.4 as well as Experiment 15. In the current implementation, we assume there is one object in each image, and in each iteration of learning, we crop a maximum likelihood image patch from each image, to be used to re-learn the template. We do not have to assume there is one object in each image, and we may simply keep all the image patches of high likelihoods, and re-learn the template from these image patches weighted by their likelihoods.

  1. Deer
  2. Cat
  3. Cat
  4. Panda
  5. Panda2
  6. Bear
  7. Lion
  8. Lioness
  9. Cougar
  10. Cheetah
  11. Cheetah 2
  12. Snow leopard
  13. Tiger
  14. Wolf head
  15. Wolf
  16. Horse 0
  17. Horse 1
  18. Horse 2
  19. Horse 3
  20. Donkey
  21. Donkey head
  22. Pony
  23. Dog
  24. Cattle
  25. Cattle head
  26. Sheep head
  27. Lamb
  28. Wildebeast
  29. Camel
  30. Elephant
  31. Kangaroo
  32. Squirell
  33. Rabbit
  34. Hammingbird
  35. King fisher
  36. Eagle
  37. Eagle head
  38. Seagull
  39. Seagull 2
  40. Oystercatcher
  41. Albatross
  42. Crane
  43. Pigeon
  44. Pigeon head
  45. Swan
  46. Egret
  47. Huron
  48. Goose
  49. Flamingo
  50. Ostrich
  51. Cormorant
  52. Bird
  53. Mockingbird
  54. Blue bird
  55. Flycatcher
  56. American robin
  57. Nutcracker
  58. Bird of joy
  59. Australia magpie
  60. Dove
  61. Pelican
  62. Duck
  63. Dragonfly
  64. Sea star
  65. Dolphin
  66. Maple
  67. Peach blossom
  68. Pear blossom
  69. Plum (mei2)
  70. Plum (li3)
  71. Bush cinquefoil
  72. Cherry
  73. Strawberry flower
  74. Cranesbill
  75. Forget me not
  76. Scarlet pimpernel
  77. Desert rose
  78. Western Springbeauty
  79. Cistus Salvifolius
  80. Hypericum chinense
  81. Mustang Clover
  82. Common linanthus
  83. Sulfur Cinquefoil
  84. Geranium
  85. Grass of Parnassus
  86. Ballon flower
  87. Canchalagua
  88. Centaury
  89. Small Wirelettuce
  90. Periwinkle
  91. Four-o'clock
  92. Fire pink
  93. Snow Trillium
  94. Bee orchid
  95. Dwarf spiderwort
  96. Lilac
  97. Bunchberry
  98. Clematis
  99. Narcissus
  100. Blue eyed grass
  101. Pretty face
  102. Muilla maritima
  103. Lily
  104. Gardenia
  105. Winter jasmine
  106. Spring starflower
  107. Starflower
  108. Starflower with 7 petals
  109. Gesar flower
  110. Cosmos flower
  111. Silene Colorata
  112. White campion
  113. Paris japonica
  114. Black-eyed susan
  115. Mayweed
  116. Chamomile
  117. Daisy
  118. Fleabane
  119. Tulip
  120. Blue Flag Iris
  121. Rose
  122. Chinese rose
  123. Violin
  124. Guitar
  125. Watch
  126. Wheel
  127. Bike
  128. Motorcycle
  129. Car
  130. Teapot
  131. Cup
  132. Model

Back to active basis homepage