Data to 7 Oct 2026

Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions

arXiv 1506.00511 ↗First posted 1 Jun 2015cs.LG cs.CV cs.NEcited by 64

Not on the map. Why?

Abstract (arXiv)

One of the main challenges in Zero-Shot Learning of visual categories is gathering semantic attributes to accompany images. Recent work has shown that learning from textual descriptions, such as Wikipedia articles, avoids the problem of having to explicitly define these attributes. We present a new model that can classify unseen categories from their textual description. Specifically, we use text features to predict the output weights of both the convolutional and the fully connected layers in a deep convolutional neural network (CNN). We take advantage of the architecture of CNNs and learn features at different layers, rather than just learning an embedding space for both modalities, as is common with existing approaches. The proposed model also allows us to automatically generate a list of pseudo- attributes for each visual category consisting of words from Wikipedia articles. We train our models end-to-end us- ing the Caltech-UCSD bird and flower datasets and evaluate both ROC and Precision-Recall curves. Our empirical results show that the proposed model significantly outperforms previous methods.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jun 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 19; 2023: 16; 2024: 7; 2025: 2; 2026: 1.

64 papers.

Sort:

By area:

2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
2021Learning to Prompt for Vision-Language Modelscited by 2,269
2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
2022Task Residual for Tuning Vision-Language Modelscited by 122
2021When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Datacited by 75
2024A Closer Look at AUROC and AUPRC under Class Imbalancecited by 56
2021Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentationcited by 53
2022Mixed Differential Privacy in Computer Visioncited by 53
2022Multitask Vision-Language Prompt Tuningcited by 51
2023Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Promptscited by 48
2021ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learningcited by 46
2021Knowledge-aware Zero-Shot Learning: Survey and Perspectivecited by 41

38 more

2022Generating Representative Samples for Few-Shot Classificationcited by 39
2022On Guiding Visual Attention with Language Specificationcited by 30
2022I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classificationcited by 27
2023Multi-modal Machine Learning in Engineering Design: A Review and Future Directionscited by 27
2021Semantics-Guided Contrastive Network for Zero-Shot Object detectioncited by 26
2021Dual Progressive Prototype Network for Generalized Zero-Shot Learningcited by 26
2023Understanding Transferable Representation Learning and Zero-shot Transfer in CLIPcited by 26
2023Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learningcited by 24
2022Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Modelscited by 22
2023Domain-Controlled Prompt Learningcited by 22
2021Fine-Grained Zero-Shot Learning with DNA as Side Informationcited by 20
2023Learning to Adapt CLIP for Few-Shot Monocular Depth Estimationcited by 19
2022EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encodercited by 18
2021Learning Robust Visual-semantic Mapping for Zero-shot Learningcited by 16
2023Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learningcited by 16
2022Towards Zero-shot Sign Language Recognitioncited by 13
2023Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Modelscited by 13
2023Cross-Modal Concept Learning and Inference for Vision-Language Modelscited by 12
2022Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attentioncited by 11
2023CoPL: Contextual Prompt Learning for Vision-Language Understandingcited by 9
2021CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervisioncited by 7
2022A Survey on Visual Transfer Learning using Knowledge Graphscited by 7
2024Conceptual Codebook Learning for Vision-Language Modelscited by 7
2021CIZSL++: Creativity Inspired Generative Zero-Shot Learningcited by 6
2023Navigating Alignment for Non-identical Client Class Sets: A Label Name-Anchored Federated Learning Frameworkcited by 6
2023Unleashing the Power of Shared Label Structures for Human Activity Recognitioncited by 6
2023SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detectioncited by 6
2021Cross Knowledge-based Generative Zero-Shot Learning Approach with Taxonomy Regularizationcited by 5
2024A separability-based approach to quantifying generalization: which layer is best?cited by 5
2021Field-Guide-Inspired Zero-Shot Learningcited by 4
2023Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignmentcited by 4
2024Visual-Semantic Decomposition and Partial Alignment for Document-based Zero-Shot Learningcited by 4
2025Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learningcited by 4
2021Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learningcited by 3
2022Contrastive Training Improves Zero-Shot Classification of Semi-structured Documentscited by 3
2024Synthesizing Knowledge-enhanced Features for Real-world Zero-shot Food Detectioncited by 3
2024An Individual Identity-Driven Framework for Animal Re-Identificationcited by 3
2021Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representationcited by 2

50 most cited of 64 All 64 (JSON)