Compositional Zero-Shot Learning

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

6 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 31 papers with code (65 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning
  26 May 2023 2 repositories listed
  In this paper, we study the problem of Compositional Zero-Shot Learning (CZSL), which is to recognize novel attribute-object combinations with pre-existing concepts.
• Learning Graph Embeddings for Open World Compositional Zero-Shot Learning
  3 May 2021 2 repositories listed
  In this work, we overcome this assumption operating on the open world setting, where no limit is imposed on the compositional space at test time, and the search space contains a large number of unseen compositions.
• Open World Compositional Zero-Shot Learning
  29 Jan 2021 2 repositories listed
  After estimating the feasibility score of each composition, we use these scores to either directly mask the output space or as a margin for the cosine similarity between visual features and compositional embeddings…
• MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning
  15 May 2025 1 repository listed Syntology ran 23 of 28 samples · 5 unverified · 28 pointer-only (licence)
  To address this issue, we propose a Multi-Stage Cross-modal Interaction (MSCI) model that effectively explores and utilizes intermediate-layer information from CLIP's visual encoder.
• Learning Clustering-based Prototypes for Compositional Zero-shot Learning
  10 Feb 2025 1 repository listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  Existing CZSL solutions typically rely on oversimplified data assumptions, e.
• Unified Framework for Open-World Compositional Zero-shot Learning
  5 Dec 2024 1 repository listed
  Open-World Compositional Zero-Shot Learning (OW-CZSL) addresses the challenge of recognizing novel compositions of known primitives and entities.
• Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning
  18 Nov 2024 1 repository listed
  Moreover, we propose attribute smoothing with auxiliary attributes generated by Large Language Model (LLM) for seen compositions, addressing the issue of overconfidence by encouraging the model to learn more attributes…
• Attention Based Simple Primitives for Open World Compositional Zero-Shot Learning
  18 Jul 2024 1 repository listed
  We are exploring Open World Compositional Zero-Shot Learning (OW-CZSL) in this study, where our test space encompasses all potential combinations of attributes and objects.
• Contextual Interaction via Primitive-based Adversarial Training For Compositional Zero-shot Learning
  21 Jun 2024 1 repository listed
  Inspired by the success of vanilla adversarial learning in Cross-Domain Few-Shot Learning, we take a step further and devise a model-agnostic and Primitive-Based Adversarial training (PBadv) method to deal with this…
• Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding
  30 Nov 2023 1 repository listed Syntology ran 4 of 11 samples · 7 unverified · 11 pointer-only (licence)
  With this in mind, we propose a simple yet effective approach to optimize VLMs in fine-grained understanding, achieving significant improvements on SPEC without compromising the zero-shot performance.
• GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learning
  9 Nov 2023 1 repository listed Syntology ran 7 of 12 samples · 5 unverified · 12 pointer-only (licence)
  In this work, we propose GIP-COL (Graph-Injected Soft Prompting for COmpositional Learning) to better explore the compositional zero-shot learning (CZSL) ability of VLMs within the prompt-based learning framework.
• Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning
  8 Aug 2023 1 repository listed Syntology ran 11 of 12 samples · 1 unverified · 12 pointer-only (licence)
  Previous works for CZSL often suffer from grasping the contextuality between attribute and object, as well as the discriminability of visual features, and the long-tailed distribution of real-world compositional data.
• Learning Conditional Attributes for Compositional Zero-Shot Learning
  29 May 2023 1 repository listed Syntology ran 6 of 9 samples · 3 unverified · 9 pointer-only (licence)
  Compositional Zero-Shot Learning (CZSL) aims to train models to recognize novel compositional concepts based on learned concepts such as attribute-object combinations.
• Prompting Language-Informed Distribution for Compositional Zero-Shot Learning
  23 May 2023 1 repository listed Syntology ran 3 of 8 samples · 5 unverified
  Compositional zero-shot learning (CZSL) task aims to recognize unseen compositional visual concepts, e.
• Learning Attention as Disentangler for Compositional Zero-shot Learning
  27 Mar 2023 1 repository listed Syntology ran 5 of 11 samples · 6 unverified
  The key to CZSL is learning the disentanglement of the attribute-object composition.
• Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
  27 Mar 2023 1 repository listed
  Recent compositional zero-shot learning (CZSL) methods adapt pre-trained vision-language models (VLMs) by constructing trainable prompts only for composed state-object pairs.
• Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning
  19 Nov 2022 1 repository listed Syntology ran 1 of 4 samples · 3 unverified
  Existing methods either learn the combined state-object representation, challenging the generalization of unseen compositions, or design two classifiers to identify state and object separately from image features,…
• Reference-Limited Compositional Zero-Shot Learning
  22 Aug 2022 1 repository listed
  Compositional zero-shot learning (CZSL) refers to recognizing unseen compositions of known visual primitives, which is an essential ability for artificial intelligence systems to learn and understand the world.
• Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning
  29 Jun 2022 1 repository listed Syntology ran 3 of 7 samples · 4 unverified · 7 pointer-only (licence)
  Some methods recognize state and object with two trained classifiers, ignoring the impact of the interaction between object and state; the other methods try to learn the joint representation of the state-object…
• Learning Invariant Visual Representations for Compositional Zero-Shot Learning
  1 Jun 2022 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions using knowledge learned from seen attribute-object compositions in the training set.
• Disentangling Visual Embeddings for Attributes and Objects
  17 May 2022 1 repository listed
  We use visual decomposed features to hallucinate embeddings that are representative for the seen and novel compositions to better regularize the learning of our model.
• KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning
  13 May 2022 1 repository listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
  The goal of open-world compositional zero-shot learning (OW-CZSL) is to recognize compositions of state and objects in images, given only a subset of them during training and no prior on the unseen compositions.
• Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
  7 Apr 2022 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  We perform additional experiments to show that CSP improves generalization to higher-order attribute-attribute-object compositions (e.
• BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning
  3 Mar 2022 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  We perform extensive experiments on over ten datasets and the proposed method achieves significant improvements on different data scarcity applications without any bells and whistles, including the tasks of long-tailed…
• Learning Single/Multi-Attribute of Object with Symmetry and Group
  9 Oct 2021 1 repository listed Syntology ran 0 of 3 samples · 3 unverified
  To model the compositional nature of these concepts, it is a good choice to learn them as transformations, e.
• Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition
  10 Aug 2021 1 repository listed
  The concept module generates semantically meaningful features for primitive concepts, whereas the visual module extracts visual features for attributes and objects from input images.
• Independent Prototype Propagation for Zero-Shot Compositionality
  1 Jun 2021 1 repository listed
  Next we propagate the independent prototypes through a compositional graph, to learn compositional prototypes of novel attribute-object combinations that reflect the dependencies of the target distribution.
• Learning Graph Embeddings for Compositional Zero-shot Learning
  3 Feb 2021 1 repository listed Syntology ran 6 of 11 samples · 5 unverified · 11 pointer-only (licence)
  In compositional zero-shot learning, the goal is to recognize unseen compositions (e.
• A causal view of compositional zero-shot recognition
  25 Jun 2020 1 repository listed
  This leads to consistent misclassification of samples from a new distribution, like new combinations of known components.
• Symmetry and Group in Attribute-Object Compositions
  1 Apr 2020 1 repository listed
  To model the compositional nature of these general concepts, it is a good choice to learn them through transformations, such as coupling and decoupling.

Syntology lines on 16 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.