1 code implementation • 6 Oct 2021 • Connor Anderson, Ryan Farrell
Challenging issues with large-scale image datasets become points of elegance for fractal pre-training: perfect label accuracy at zero cost; no need to store/transmit large image archives; no privacy/demographic bias/concerns of inappropriate content, as no humans are pictured; limitless supply and diversity of images; and the images are free/open-source.
no code implementations • 7 Sep 2021 • Matthew Gwilliam, Adam Teuscher, Connor Anderson, Ryan Farrell
From this analysis, we both highlight the importance of reporting and comparing methods based on information beyond overall accuracy, as well as point out techniques that mitigate variance in FGVC results.
no code implementations • 23 Jun 2020 • Connor Anderson, Matt Gwilliam, Adam Teuscher, Andrew Merrill, Ryan Farrell
In fine-grained visual categorization (FGVC), there is a near-singular focus in pursuit of attaining state-of-the-art (SOTA) accuracy.
no code implementations • 23 May 2018 • Pei Guo, Ryan Farrell
For filter-level interpretation, we represent the concepts a filter encodes with a probability distribution of visual attributes.
no code implementations • 27 Jan 2018 • Pei Guo, Ryan Farrell
Rather than representing an object by regions aligned to image axes, the proposed representation characterizes appearance relative to the object's pose using pose-aligned patches whose features are robust to variations in pose, scale and rotation.
Ranked #14 on Fine-Grained Image Classification on NABirds (using extra training data)
1 code implementation • ECCV 2018 • Abhimanyu Dubey, Otkrist Gupta, Pei Guo, Ramesh Raskar, Ryan Farrell, Nikhil Naik
Fine-Grained Visual Classification (FGVC) datasets contain small sample sizes, along with significant intra-class variation and inter-class similarity.
Ranked #15 on Fine-Grained Image Classification on Stanford Dogs
no code implementations • CVPR 2015 • Grant Van Horn, Steve Branson, Ryan Farrell, Scott Haber, Jessie Barry, Panos Ipeirotis, Pietro Perona, Serge Belongie
We worked with bird experts to measure the quality of popular datasets like CUB-200-2011 and ImageNet and found class label error rates of at least 4%.
no code implementations • ICCV 2013 • Ning Zhang, Ryan Farrell, Forrest Iandola, Trevor Darrell
Recognizing objects in fine-grained domains can be extremely challenging due to the subtle differences between subcategories.
Ranked #25 on Fine-Grained Image Classification on CUB-200-2011