Papers › Learning Robust Visual-Semantic Embeddings

Learning Robust Visual-Semantic Embeddings

17 Mar 2017ICCV 2017 10arXiv:1703.05908archive 2025-07-28

Yao-Hung Hubert Tsai, Liang-Kang Huang, Ruslan Salakhutdinov

Many of the existing methods for learning joint embedding of images and text use only supervised information from paired images and its textual attributes. Taking advantage of the recent success of unsupervised learning in deep neural networks, we propose an end-to-end learning framework that is able to extract more robust multi-modal representations across domains. The proposed method combines representation learning models (i.e., auto-encoders) together with cross-domain learning criteria (i.e., Maximum Mean Discrepancy loss) to learn joint embeddings for semantic and visual features. A novel technique of unsupervised-data adaptation inference is introduced to construct more comprehensive embeddings for both labeled and unlabeled data. We evaluate our method on Animals with Attributes and Caltech-UCSD Birds 200-2011 dataset with a wide range of applications, including zero and few-shot image recognition and retrieval, from inductive to transductive settings. Empirically, we show that our framework improves over the current state of the art on many of the considered tasks.

PaperPDFConference PDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Generalized Few-Shot LearningRepresentation LearningRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Generalized Few-Shot Learning AwA2 REVISE Per-Class Accuracy (1-shot) 56.1 #6 of 6 Archive leaderboard report
Generalized Few-Shot Learning AwA2 REVISE Per-Class Accuracy (10-shots) 67.8 #6 of 6 Archive leaderboard report
Generalized Few-Shot Learning AwA2 REVISE Per-Class Accuracy (2-shots) 60.3 #6 of 6 Archive leaderboard report
Generalized Few-Shot Learning AwA2 REVISE Per-Class Accuracy (5-shots) 64.1 #6 of 6 Archive leaderboard report
Generalized Few-Shot Learning CUB REVISE Per-Class Accuracy (2-shots) 41.1 #5 of 5 Archive leaderboard report
Generalized Few-Shot Learning CUB REVISE Per-Class Accuracy (1-shot) 36.3 #5 of 5 Archive leaderboard report
Generalized Few-Shot Learning CUB REVISE Per-Class Accuracy (10-shots) 50.9 #5 of 5 Archive leaderboard report
Generalized Few-Shot Learning CUB REVISE Per-Class Accuracy (5-shots) 44.6 #5 of 5 Archive leaderboard report
Generalized Few-Shot Learning SUN REVISE Per-Class Accuracy (1-shot) 27.4 #5 of 5 Archive leaderboard report
Generalized Few-Shot Learning SUN REVISE Per-Class Accuracy (10-shots) 40.8 #5 of 5 Archive leaderboard report
Generalized Few-Shot Learning SUN REVISE Per-Class Accuracy (2-shots) 33.4 #5 of 5 Archive leaderboard report
Generalized Few-Shot Learning SUN REVISE Per-Class Accuracy (5-shots) 37.4 #5 of 5 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