Papers › Learning Deep Representations of Fine-grained Visual Descriptions

Learning Deep Representations of Fine-grained Visual Descriptions

17 May 2016CVPR 2016 6arXiv:1605.05395archive 2025-07-28

Scott Reed, Zeynep Akata, Bernt Schiele, Honglak Lee

State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded vectors describing shared characteristics among categories. Despite good performance, attributes have limitations: (1) finer-grained recognition requires commensurately more attributes, and (2) attributes do not provide a natural language interface. We propose to overcome these limitations by training neural language models from scratch; i.e. without pre-training and only consuming words and characters. Our proposed models train end-to-end to align with the fine-grained and category-specific content of images. Natural language provides a flexible and compact way of encoding only the salient visual aspects for distinguishing categories. By training on raw text, our model can do inference on raw text as well, providing humans a familiar mode both for annotation and retrieval. Our model achieves strong performance on zero-shot text-based image retrieval and significantly outperforms the attribute-based state-of-the-art for zero-shot classification on the Caltech UCSD Birds 200-2011 dataset.

PaperPDFConference PDFCode

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

Code

Maymaher/StackGANv2 mentioned on GitHubpytorch report
Vigneshthanga/stackGAN-v2 mentioned on GitHubpytorch report
Vishal-V/StackGAN mentioned on GitHubtfMIT report
hanzhanggit/StackGAN-v2 mentioned on GitHubpytorchMIT report
priscillalui/StackGAN-Stories mentioned on GitHubpytorch report
reedscot/cvpr2016 mentioned on GitHubMIT report
rightlit/StackGAN-v2-rev mentioned on GitHubpytorchMIT 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

AttributeImage RetrievalRetrievalZero-Shot Learning

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) DA-SJE Reed et al. (2016) Accuracy 50.9 #2 of 4 Archive leaderboard report
Few-Shot Image Classification CUB 200 50-way (0-shot) DS-SJE Reed et al. (2016) Accuracy 50.4 #3 of 4 Archive leaderboard report
Few-Shot Image Classification CUB-200-2011 - 0-Shot Word CNN-RNN (DS-SJE Embedding) AP50 48.7 #1 of 5 Archive leaderboard report
Few-Shot Image Classification CUB-200-2011 - 0-Shot Word CNN-RNN (DS-SJE Embedding) Top-1 Accuracy 56.8% #1 of 5 Archive leaderboard report
Few-Shot Image Classification Flowers-102 - 0-Shot Word CNN-RNN (DS-SJE Embedding) AP50 59.6 #1 of 1 Archive leaderboard report
Few-Shot Image Classification Flowers-102 - 0-Shot Word CNN-RNN (DS-SJE Embedding) Accuracy 65.6% #1 of 1 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