Circle Loss: A Unified Perspective of Pair Similarity Optimization

by   Yifan Sun, et al.

This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity s_p and minimize the between-class similarity s_n. We find a majority of loss functions, including the triplet loss and the softmax plus cross-entropy loss, embed s_n and s_p into similarity pairs and seek to reduce (s_n-s_p). Such an optimization manner is inflexible, because the penalty strength on every single similarity score is restricted to be equal. Our intuition is that if a similarity score deviates far from the optimum, it should be emphasized. To this end, we simply re-weight each similarity to highlight the less-optimized similarity scores. It results in a Circle loss, which is named due to its circular decision boundary. The Circle loss has a unified formula for two elemental deep feature learning approaches, i.e. learning with class-level labels and pair-wise labels. Analytically, we show that the Circle loss offers a more flexible optimization approach towards a more definite convergence target, compared with the loss functions optimizing (s_n-s_p). Experimentally, we demonstrate the superiority of the Circle loss on a variety of deep feature learning tasks. On face recognition, person re-identification, as well as several fine-grained image retrieval datasets, the achieved performance is on par with the state of the art.


page 1

page 2

page 3

page 4


Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition

The goal of face recognition (FR) can be viewed as a pair similarity opt...

Unified Loss of Pair Similarity Optimization for Vision-Language Retrieval

There are two popular loss functions used for vision-language retrieval,...

Distribution Context Aware Loss for Person Re-identification

To learn the optimal similarity function between probe and gallery image...

Instance Similarity Deep Hashing for Multi-Label Image Retrieval

Hash coding has been widely used in the approximate nearest neighbor sea...

Exploiting Class Similarity for Machine Learning with Confidence Labels and Projective Loss Functions

Class labels used for machine learning are relatable to each other, with...

Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning

A family of loss functions built on pair-based computation have been pro...

Learning Deep Embeddings with Histogram Loss

We suggest a loss for learning deep embeddings. The new loss does not in...

Please sign up or login with your details

Forgot password? Click here to reset