Papers › Evaluation of Output Embeddings for Fine-Grained Image Classification

Evaluation of Output Embeddings for Fine-Grained Image Classification

30 Sep 2014CVPR 2015 6arXiv:1409.8403archive 2025-07-28

Zeynep Akata, Scott Reed, Daniel Walter, Honglak Lee, Bernt Schiele

Image classification has advanced significantly in recent years with the availability of large-scale image sets. However, fine-grained classification remains a major challenge due to the annotation cost of large numbers of fine-grained categories. This project shows that compelling classification performance can be achieved on such categories even without labeled training data. Given image and class embeddings, we learn a compatibility function such that matching embeddings are assigned a higher score than mismatching ones; zero-shot classification of an image proceeds by finding the label yielding the highest joint compatibility score. We use state-of-the-art image features and focus on different supervised attributes and unsupervised output embeddings either derived from hierarchies or learned from unlabeled text corpora. We establish a substantially improved state-of-the-art on the Animals with Attributes and Caltech-UCSD Birds datasets. Most encouragingly, we demonstrate that purely unsupervised output embeddings (learned from Wikipedia and improved with fine-grained text) achieve compelling results, even outperforming the previous supervised state-of-the-art. By combining different output embeddings, we further improve results.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

inars/developing_mc_for_zsl mentioned on GitHub report
mvp18/Popular-ZSL-Algorithms mentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationFew-Shot Image ClassificationFine-Grained Image ClassificationGeneral ClassificationImage ClassificationZero-Shot Action RecognitionZero-Shot Learningimage-classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CUB 200 50-way (0-shot) SJE Akata et al. (2015) Accuracy 50.1 #4 of 4 Archive leaderboard report
Few-Shot Image Classification CUB-200 - 0-Shot Learning SJE Accuracy 50.1% #2 of 3 Archive leaderboard report
Few-Shot Image Classification CUB-200-2011 - 0-Shot SJE Top-1 Accuracy 50.1% #3 of 5 Archive leaderboard report
Zero-Shot Action Recognition HMDB51 SJE(word embedding) Top-1 Accuracy 13.3 #28 of 29 Archive leaderboard report
Zero-Shot Action Recognition Kinetics SJE(Word Embedding) Top-1 Accuracy 22.3 #20 of 20 Archive leaderboard report
Zero-Shot Action Recognition Kinetics SJE(Word Embedding) Top-5 Accuracy 48.2 #20 of 20 Archive leaderboard report
Zero-Shot Action Recognition Olympics SJE(Atrribute) Top-1 Accuracy 47.5 #6 of 9 Archive leaderboard report
Zero-Shot Action Recognition Olympics SJE(Word Embedding) Top-1 Accuracy 28.6 #9 of 9 Archive leaderboard report
Zero-Shot Action Recognition UCF101 SJE(Attribute) Top-1 Accuracy 12.0 #33 of 35 Archive leaderboard report
Zero-Shot Action Recognition UCF101 SJE(Word Embedding) Top-1 Accuracy 9.9 #35 of 35 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections