Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning

@inproceedings{Cacheux2020WeblySS,
  title={Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning},
  author={Yannick Le Cacheux and A. Popescu and H. Borgne},
  booktitle={ACCV},
  year={2020}
}
Zero-shot learning (ZSL) makes object recognition in images possible in absence of visual training data for a part of the classes from a dataset. When the number of classes is large, classes are usually represented by semantic class prototypes learned automatically from unannotated text collections. This typically leads to much lower performances than with manually designed semantic prototypes such as attributes. While most ZSL works focus on the visual aspect and reuse standard semantic… Expand
2 Citations
Revisiting Document Representations for Large-Scale Zero-Shot Learning
  • PDF

References

SHOWING 1-10 OF 61 REFERENCES
Zero-Shot Recognition via Semantic Embeddings and Knowledge Graphs
  • 255
  • PDF
Multi-cue Zero-Shot Learning with Strong Supervision
  • 105
  • PDF
Zero-Shot Learning via Semantic Similarity Embedding
  • 423
  • PDF
DeViSE: A Deep Visual-Semantic Embedding Model
  • 1,585
  • Highly Influential
  • PDF
Preserving Semantic Relations for Zero-Shot Learning
  • 116
  • PDF
Zero-Shot Learning by Convex Combination of Semantic Embeddings
  • 646
  • Highly Influential
  • PDF
Zero-Shot Learning Through Cross-Modal Transfer
  • 1,006
  • PDF
Evaluation of output embeddings for fine-grained image classification
  • 640
  • PDF
Zero-Shot Classification by Generating Artificial Visual Features
  • 6
  • PDF
Modeling Inter and Intra-Class Relations in the Triplet Loss for Zero-Shot Learning
  • 24
  • PDF
...
1
2
3
4
5
...