No Fuss Distance Metric Learning Using Proxies
Citations
549 citations
540 citations
Cites background or methods from "No Fuss Distance Metric Learning Us..."
...The implementation details are comparable to [11] and [12]....
[...]
...Unlike in [11] where only the embedding extractor part is used during test time with the auxiliary proxies thrown away, we keep the entirety of the network....
[...]
...[11] reformulated the loss by assigning proxies p(·) to training examples according to the class labels...
[...]
...Imprinted weights and Proxy-NCA are both trained with the softmax cross-entropy loss....
[...]
...The proxy-based loss, from which we have derived our method, upper bounds the instance-based triplet loss [11]....
[...]
341 citations
Cites background or methods from "No Fuss Distance Metric Learning Us..."
...Supervised embedding learning methods have been studied to achieve such objectives and demonstrate impressive capabilities in various vision tasks [28, 30, 53]....
[...]
...Most of them are designed on top of pairwise [12, 30] or triplet relationships [13, 29]....
[...]
...The pre-trained Inception-V1 [39] on ImageNet is used as the backbone network following existing methods [30, 32, 37]....
[...]
...In testing phase, a single center-cropped image is adopted for fine-grained recognition as in [30]....
[...]
...For data augmentation, the images are randomly cropped at size 227×227 with random horizontal flipping following [21, 30]....
[...]
306 citations
Cites background from "No Fuss Distance Metric Learning Us..."
...A simple cross-entropy loss would work, but we found empirically that the NCA loss [10,28] converged faster....
[...]
...For each class, the normalized weight vector acts as a single proxy [28], towards which the learning procedure pushes all samples in the class....
[...]
301 citations
References
40,257 citations
30,811 citations
17,184 citations
11,804 citations
10,447 citations
"No Fuss Distance Metric Learning Us..." refers methods in this paper
...We used the TensorFlow Deep Learning framework [1] for all methods described below....
[...]