0 citations0 references

Fine-grained recognition without part annotations

2015pp. 5546–5555

Citations Over TimeTop 1% of 2015 papers

Jonathan Krause, Hailin Jin, Shuicheng Yan, Li Fei-Fei

Abstract

Scaling up fine-grained recognition to all domains of fine-grained objects is a challenge the computer vision community will need to face in order to realize its goal of recognizing all object categories. Current state-of-the-art techniques rely heavily upon the use of keypoint or part annotations, but scaling up to hundreds or thousands of domains renders this annotation cost-prohibitive for all but the most important categories. In this work we propose a method for fine-grained recognition that uses no part annotations. Our method is based on generating parts using co-segmentation and alignment, which we combine in a discriminative mixture. Experimental results show its efficacy, demonstrating state-of-the-art results even when compared to methods that use part annotations during training.

Related Papers

Stable Discriminative Dictionary Learning Via Discriminative Deviation(2012)
→ Discriminative Regions: A Substrate for Analyzing Life-Logging Image Sequences(2014)2 cited
On the Important Content Characters about Annotation of Xiaojing by Tang Xuan_zong(2005)
→ Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback(2023)