Softtriple loss: Deep metric learning without triplet sampling
Distance metric learning (DML) is to learn the embeddings where examples from the same
class are closer than examples from different classes. It can be cast as an optimization …
class are closer than examples from different classes. It can be cast as an optimization …
Deep metric learning via lifted structured feature embedding
Learning the distance metric between pairs of examples is of great importance for learning
and visual recognition. With the remarkable success from the state of the art convolutional …
and visual recognition. With the remarkable success from the state of the art convolutional …
Repmet: Representative-based metric learning for classification and few-shot object detection
Distance metric learning (DML) has been successfully applied to object classification, both
in the standard regime of rich training data and in the few-shot scenario, where each …
in the standard regime of rich training data and in the few-shot scenario, where each …
Object-part attention model for fine-grained image classification
Fine-grained image classification is to recognize hundreds of subcategories belonging to
the same basic-level category, such as 200 subcategories belonging to the bird, which is …
the same basic-level category, such as 200 subcategories belonging to the bird, which is …
Learning deep embeddings with histogram loss
E Ustinova, V Lempitsky - Advances in neural information …, 2016 - proceedings.neurips.cc
We suggest a new loss for learning deep embeddings. The key characteristics of the new
loss is the absence of tunable parameters and very good results obtained across a range of …
loss is the absence of tunable parameters and very good results obtained across a range of …
Cross-dimensional weighting for aggregated deep convolutional features
We propose a simple and straightforward way of creating powerful image representations
via cross-dimensional weighting and aggregation of deep convolutional neural network …
via cross-dimensional weighting and aggregation of deep convolutional neural network …
Group-sensitive triplet embedding for vehicle reidentification
The widespread use of surveillance cameras toward smart and safe cities poses the critical
but challenging problem of vehicle reidentification (Re-ID). The state-of-the-art research …
but challenging problem of vehicle reidentification (Re-ID). The state-of-the-art research …
Trends in vehicle re-identification past, present, and future: A comprehensive review
Vehicle Re-identification (re-id) over surveillance camera network with non-overlapping field
of view is an exciting and challenging task in intelligent transportation systems (ITS). Due to …
of view is an exciting and challenging task in intelligent transportation systems (ITS). Due to …
Borrowing treasures from the wealthy: Deep transfer learning through selective joint fine-tuning
Deep neural networks require a large amount of labeled training data during supervised
learning. However, collecting and labeling so much data might be infeasible in many cases …
learning. However, collecting and labeling so much data might be infeasible in many cases …
Darkrank: Accelerating deep metric learning via cross sample similarities transfer
We have witnessed rapid evolution of deep neural network architecture design in the past
years. These latest progresses greatly facilitate the developments in various areas such as …
years. These latest progresses greatly facilitate the developments in various areas such as …