No article text was recorded for this version.
compositional zero-shot generalization
Version 1 of 150 papers59 conceptsfrozen 2026-10-04
Papers in this version
- Blog: PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck
- Blog: Zero-data Learning of New Tasks
- Blog: Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-Training Framework
- Blog: SLIP-RS: Structured-Attribute Language-Image Pre-Training for Remote Sensing Object Detection
- Blog: Deep Learning Models Connecting Images and Text: A Primer for Radiologists
- Blog: Handwritten Word Spotting with Corrected Attributes
- Blog: Compositional Few-Shot Recognition with Primitive Discovery and Enhancing
- Blog: Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment
- Blog: Interpretable Few-Shot Retinal Disease Diagnosis with Concept-Guided Prompting of Vision-Language Models
- Blog: MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training for X-ray Diagnosis
- Blog: Diverse Image Captioning with Context-Object Split Latent Spaces
- Blog: Linear Spaces of Meanings: Compositional Structures in Vision-Language Models
- Blog: Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And Detection
- Blog: Learnable Visual Words for Interpretable Image Recognition
- Blog: Similarity by Composition
- Blog: HierCode: A Lightweight Hierarchical Codebook for Zero-shot Chinese Text Recognition
- Blog: MEDICAL IMAGE UNDERSTANDING WITH PRETRAINED VISION LANGUAGE MODELS: A COMPREHENSIVE STUDY
- Blog: Identifying Latent Concepts and Structures for Generalized Category Discovery
- Blog: An embarrassingly simple approach to zero-shot learning
- Blog: Recognizing human actions by attributes
- Blog: Open-Set Representation Learning through Combinatorial Embedding
- Blog: RD-GAN: Few/Zero-Shot Chinese Character Style Transfer via Radical Decomposition and Rendering
- Blog: Improving Information Extraction from Images with Learned Semantic Models
- Blog: AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation
- Blog: Trajectory-based Radical Analysis Network for Online Handwritten Chinese Character Recognition
- Blog: DenseRAN for Offline Handwritten Chinese Character Recognition
- Blog: A New Few-shot Segmentation Network Based on Class Representation
- Blog: Multi-Resolution Language Grounding with Weak Supervision
- Blog: STNN-DDI: A Substructure-aware Tensor Neural Network to Predict Drug-Drug Interactions
- Blog: Overcoming both Domain Shift and Label Shift for Referring Video Segmentation
- Blog: Link the Head to the "Beak": Zero Shot Learning from Noisy Text Description at Part Precision
- Blog: Attribute-Based Robotic Grasping with One-Grasp Adaptation
- Blog: The American Sign Language Knowledge Graph: Infusing ASL Models with Linguistic Knowledge
- Blog: ZERO - Detect objects without training examples by knowing their parts
- Blog: Contrastive Learning of Semantic Concepts for Open-set Cross-domain Retrieval
- Blog: Learning Compositional Representations for Few-Shot Recognition
- Blog: Editorial for the ICMR 2019 special issue
- Blog: A Hierarchical Decoding Model For Spoken Language Understanding From Unaligned Data
- Blog: RZCR: Zero-shot Character Recognition via Radical-based Reasoning
- Blog: Contributions of Shape, Texture, and Color in Visual Recognition
- Blog: 'Eyes of a Hawk and Ears of a Fox': Part Prototype Network for Generalized Zero-Shot Learning
- Blog: Compressing Unknown Images With Product Quantizer for Efficient Zero-Shot Classification
- Blog: MetaReVision: Meta-Learning with Retrieval for Visually Grounded Compositional Concept Acquisition
- Blog: Fine-grained Entity Typing via Label Reasoning
- Blog: Adversarial Attribute-Image Person Re-identification
- Blog: VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning
- Blog: ProtoNCD: Prototypical Parts for Interpretable Novel Class Discovery
- Blog: Open-Set Text Recognition via Character-Context Decoupling
- Blog: Learning to Recognize Novel Objects in One Shot through Human-Robot Interactions in Natural Language Dialogues
- Blog: Graph Knows Unknowns: Reformulate Zero-Shot Learning as Sample-Level Graph Recognition
History & citation
Current · Permanent link
- This direction split from Attribute Decomposition for Zero Shot Generalization (66% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_compositional_zero_shot_generalization_df92de12,
title = {compositional zero-shot generalization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/compositional-zero-shot-generalization/rdr_df92de1245ba4b0caa5e392e5d8a6853},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_compositional_zero_shot_generalization_df92de12_v1,
title = {compositional zero-shot generalization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/compositional-zero-shot-generalization/rdr_df92de1245ba4b0caa5e392e5d8a6853/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}