SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1903.06150 · 2019

Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Learning subtle yet discriminative features (e.g., beak and eyes for a bird) plays a significant role in fine-grained image recognition. Existing attention-based approaches localize and amplify significant parts to learn fine-grained details, which often suffer from a limited number of parts and heavy computational cost. In this paper, we propose to learn such fine-grained features from hundreds of part proposals by Trilinear Attention Sampling Network (TASN) in an efficient teacher-student manner. Specifically, TASN consists of 1) a trilinear attention module, which generates attention maps by modeling the inter-channel relationships, 2) an attention-based sampler which highlights attended parts with high resolution, and 3) a feature distiller, which distills part features into a global one by weight sharing and feature preserving strategies. Extensive experiments verify that TASN yields the best performance under the same settings with the most competitive approaches, in iNaturalist-2017, CUB-Bird, and Stanford-Cars datasets.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1903.06150")
get_code_for_paper("1903.06150")
have("1903.06150")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1903.06150.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1903.06150.svg)](https://syntology.ai/paper/1903.06150)

Connect an agent — have() is free.