Grafit: Learning fine-grained image representations with coarse labels

11/25/2020
by   Hugo Touvron, et al.
0

This paper tackles the problem of learning a finer representation than the one provided by training labels. This enables fine-grained category retrieval of images in a collection annotated with coarse labels only. Our network is learned with a nearest-neighbor classifier objective, and an instance loss inspired by self-supervised learning. By jointly leveraging the coarse labels and the underlying fine-grained latent space, it significantly improves the accuracy of category-level retrieval methods. Our strategy outperforms all competing methods for retrieving or classifying images at a finer granularity than that available at train time. It also improves the accuracy for transfer learning tasks to fine-grained datasets, thereby establishing the new state of the art on five public benchmarks, like iNaturalist-2018.

READ FULL TEXT

page 1

page 17

page 19

page 20

page 21

page 22

research
10/14/2022

Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning

Novel category discovery aims at adapting models trained on known catego...
research
08/16/2022

Reinforcement Learning to Rank with Coarse-grained Labels

Ranking lies at the core of many Information Retrieval (IR) tasks. While...
research
08/22/2021

Efficient Algorithms for Learning from Coarse Labels

For many learning problems one may not have access to fine grained label...
research
05/16/2020

Radial Loss for Learning Fine-grained Video Similarity Metric

In this paper, we propose the Radial Loss which utilizes category and su...
research
02/14/2019

MultiGrain: a unified image embedding for classes and instances

MultiGrain is a network architecture producing compact vector representa...
research
03/03/2020

Discover Your Social Identity from What You Tweet: a Content Based Approach

An identity denotes the role an individual or a group plays in highly di...
research
07/17/2023

Divide Classify: Fine-Grained Classification for City-Wide Visual Place Recognition

Visual Place recognition is commonly addressed as an image retrieval pro...

Please sign up or login with your details

Forgot password? Click here to reset