# Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning

arXiv: https://arxiv.org/abs/2303.15230 · HTML: https://mlsanity.com/paper/2303.15230/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 36 of its 48 references that are in the map.
- First posted on arXiv 27 Mar 2023.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Training Neural Networks with Fixed Sparse Masks](https://mlsanity.com/paper/2111.09839/) (2021)
- [Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models](https://mlsanity.com/paper/2203.06904/) (2022)
- [Unified Vision and Language Prompt Learning](https://mlsanity.com/paper/2210.07225/) (2022)
- [Task-Driven Modular Networks for Zero-Shot Compositional Learning](https://mlsanity.com/paper/1905.05908/) (2019)
- [Learning Graph Embeddings for Compositional Zero-shot Learning](https://mlsanity.com/paper/2102.01987/) (2021)
- [Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2101.12609/) (2021)
- [Symmetry and Group in Attribute-Object Compositions](https://mlsanity.com/paper/2004.00587/) (2020)
- [Learning to Compose Soft Prompts for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2204.03574/) (2022)
- [Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2206.14475/) (2022)
- [Learning Graph Embeddings for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2105.01017/) (2021)
- [KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2205.06784/) (2022)
- [Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2211.10681/) (2022)

## Built on by (most cited first, 27 of 27)

- [Prompting Language-Informed Distribution for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.14428/) (2023)
- [Learning Clustering-based Prototypes for Compositional Zero-shot Learning](https://mlsanity.com/paper/2502.06501/) (2025)
- [Compositional Zero-shot Learning via Progressive Language-based Observations](https://mlsanity.com/paper/2311.14749/) (2023)
- [M2IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension](https://mlsanity.com/paper/2407.01131/) (2024)
- [TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2408.08703/) (2024)
- [On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey](https://mlsanity.com/paper/2408.04879/) (2024)
- [FlowComposer: Composable Flows for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2603.16641/) (2026)
- [Learning Visual Proxy for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2501.13859/) (2025)
- [A Conditional Probability Framework for Compositional Zero-shot Learning](https://mlsanity.com/paper/2507.17377/) (2025)
- [MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning](https://mlsanity.com/paper/2406.12757/) (2024)
- [Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2411.12584/) (2024)
- [Learning Primitive Relations for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2501.14308/) (2025)
- [MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2505.10289/) (2025)
- [CAMS: Towards Compositional Zero-Shot Learning via Gated Cross-Attention and Multi-Space Disentanglement](https://mlsanity.com/paper/2511.16378/) (2025)
- [H2em: Learning Hierarchical Hyperbolic Embeddings for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2512.20029/) (2025)
- [Training-free Conditional Image Embedding Framework Leveraging Large Vision Language Models](https://mlsanity.com/paper/2512.21860/) (2025)
- [Reachability Is Not Generalization: Understanding Verb--Noun Decomposition in Assembly Action Recognition](https://mlsanity.com/paper/2610.00064/) (2026)
- [Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2408.17083/) (2024)
- [Semantically Guided Dynamic Visual Prototype Refinement for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2501.07114/) (2025)
- [EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2506.20986/) (2025)
- [SalientFusion: Context-Aware Compositional Zero-Shot Food Recognition](https://mlsanity.com/paper/2509.03873/) (2025)
- [Prompt-Based Continual Compositional Zero-Shot Learning](https://mlsanity.com/paper/2512.09172/) (2025)
- [Structure-aware Prompt Adaptation from Seen to Unseen for Open-Vocabulary Compositional Zero-Shot Learning](https://mlsanity.com/paper/2603.03815/) (2026)
- [Progressive Reasoning with Primitive Correction for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2607.05911/) (2026)
- [DIFFCZSL: Compositional Zero-Shot Learning Regularized by Diffusion Representations](https://mlsanity.com/paper/2608.19871/) (2026)
- [From Model Patterns to Abstract Semantics in Compositional Zero-Shot Learning](https://mlsanity.com/paper/2609.15649/) (2026)
- [From Transformation to Target State: Rethinking Query Representation for Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2610.05993/) (2026)

## Abstract (arXiv)

Recent compositional zero-shot learning (CZSL) methods adapt pre-trained vision-language models (VLMs) by constructing trainable prompts only for composed state-object pairs. Relying on learning the joint representation of seen compositions, these methods ignore the explicit modeling of the state and object, thus limiting the exploitation of pre-trained knowledge and generalization to unseen compositions. With a particular focus on the universality of the solution, in this work, we propose a novel paradigm for CZSL models that establishes three identification branches (i.e., Multi-Path) to jointly model the state, object, and composition. The presented Troika is our implementation that aligns the branch-specific prompt representations with decomposed visual features. To calibrate the bias between semantically similar multi-modal representations, we further devise a Cross-Modal Traction module into Troika that shifts the prompt representation towards the current visual content. We conduct extensive experiments on three popular benchmarks, where our method significantly outperforms existing methods in both closed-world and open-world settings. The code will be available at https://github.com/bighuang624/Troika.