# ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing

arXiv: https://arxiv.org/abs/2303.02437 · HTML: https://mlsanity.com/paper/2303.02437/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 66 of its 84 references that are in the map.
- First posted on arXiv 4 Mar 2023.

## Builds on (most cited first, 30 of 66)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [Unified Vision-Language Pre-Training for Image Captioning and VQA](https://mlsanity.com/paper/1909.11059/) (2019)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [nocaps: novel object captioning at scale](https://mlsanity.com/paper/1812.08658/) (2018)
- [Meshed-Memory Transformer for Image Captioning](https://mlsanity.com/paper/1912.08226/) (2019)
- [How Much Can CLIP Benefit Vision-and-Language Tasks?](https://mlsanity.com/paper/2107.06383/) (2021)
- [Attention on Attention for Image Captioning](https://mlsanity.com/paper/1908.06954/) (2019)
- [Auto-Encoding Scene Graphs for Image Captioning](https://mlsanity.com/paper/1812.02378/) (2018)
- [Exploring Visual Relationship for Image Captioning](https://mlsanity.com/paper/1809.07041/) (2018)
- [Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding](https://mlsanity.com/paper/2103.15358/) (2021)
- [X-Linear Attention Networks for Image Captioning](https://mlsanity.com/paper/2003.14080/) (2020)
- [Scaling Up Vision-Language Pre-training for Image Captioning](https://mlsanity.com/paper/2111.12233/) (2021)
- [Zero-Shot Object Detection](https://mlsanity.com/paper/1804.04340/) (2018)
- [BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model](https://mlsanity.com/paper/1902.04094/) (2019)

## Built on by (most cited first, 30 of 33)

- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [Caption Anything: Interactive Image Description with Diverse Multimodal Controls](https://mlsanity.com/paper/2305.02677/) (2023)
- [Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation](https://mlsanity.com/paper/2502.20056/) (2025)
- [MeaCap: Memory-Augmented Zero-shot Image Captioning](https://mlsanity.com/paper/2403.03715/) (2024)
- [LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting](https://mlsanity.com/paper/2305.19821/) (2023)
- [HICEScore: A Hierarchical Metric for Image Captioning Evaluation](https://mlsanity.com/paper/2407.18589/) (2024)
- [Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models](https://mlsanity.com/paper/2505.07209/) (2025)
- [A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes](https://mlsanity.com/paper/2403.07469/) (2024)
- [PriorRG: Prior-Guided Contrastive Pre-training and Coarse-to-Fine Decoding for Chest X-ray Report Generation](https://mlsanity.com/paper/2508.05353/) (2025)
- [Image Captioning with Multi-Context Synthetic Data](https://mlsanity.com/paper/2305.18072/) (2023)
- [EditScribe: Non-Visual Image Editing with Natural Language Verification Loops](https://mlsanity.com/paper/2408.06632/) (2024)
- [ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles](https://mlsanity.com/paper/2306.16649/) (2023)
- [MemBench: Memorized Image Trigger Prompt Dataset for Diffusion Models](https://mlsanity.com/paper/2407.17095/) (2024)
- [ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interaction](https://mlsanity.com/paper/2504.01472/) (2025)
- [AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning](https://mlsanity.com/paper/2507.12841/) (2025)
- [Visual Captioning at Will: Describing Images and Videos Guided by a Few Stylized Sentences](https://mlsanity.com/paper/2307.16399/) (2023)
- [Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights](https://mlsanity.com/paper/2407.11449/) (2024)
- [Visual Zero-Shot E-Commerce Product Attribute Value Extraction](https://mlsanity.com/paper/2502.15979/) (2025)
- [Improving Generalization of Image Captioning with Unsupervised Prompt Learning](https://mlsanity.com/paper/2308.02862/) (2023)
- [CIC-BART-SSA: Controllable Image Captioning with Structured Semantic Augmentation](https://mlsanity.com/paper/2407.11393/) (2024)
- [Fine-grained length controllable video captioning with ordinal embeddings](https://mlsanity.com/paper/2408.15447/) (2024)
- [Explaining Domain Shifts in Language: Concept erasing for Interpretable Image Classification](https://mlsanity.com/paper/2503.18483/) (2025)
- [Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis](https://mlsanity.com/paper/2408.04909/) (2024)
- [CLIP-Free, Label Free, Unsupervised Concept Bottleneck Models](https://mlsanity.com/paper/2503.10981/) (2025)
- [Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation](https://mlsanity.com/paper/2510.06131/) (2025)
- [Text-Only Training for Image Captioning with Retrieval Augmentation and Modality Gap Correction](https://mlsanity.com/paper/2512.04309/) (2025)
- [TROPE: TRaining-Free Object-Part Enhancement for Seamlessly Improving Fine-Grained Zero-Shot Image Captioning](https://mlsanity.com/paper/2409.19960/) (2024)
- [Semantically Guided Dynamic Visual Prototype Refinement for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2501.07114/) (2025)
- [The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning](https://mlsanity.com/paper/2503.23679/) (2025)
- [Group-based Distinctive Image Captioning with Memory Difference Encoding and Attention](https://mlsanity.com/paper/2504.02496/) (2025)

## Abstract (arXiv)

Zero-shot capability has been considered as a new revolution of deep learning, letting machines work on tasks without curated training data. As a good start and the only existing outcome of zero-shot image captioning (IC), ZeroCap abandons supervised training and sequentially searches every word in the caption using the knowledge of large-scale pretrained models. Though effective, its autoregressive generation and gradient-directed searching mechanism limit the diversity of captions and inference speed, respectively. Moreover, ZeroCap does not consider the controllability issue of zero-shot IC. To move forward, we propose a framework for Controllable Zero-shot IC, named ConZIC. The core of ConZIC is a novel sampling-based non-autoregressive language model named GibbsBERT, which can generate and continuously polish every word. Extensive quantitative and qualitative results demonstrate the superior performance of our proposed ConZIC for both zero-shot IC and controllable zero-shot IC. Especially, ConZIC achieves about 5x faster generation speed than ZeroCap, and about 1.5x higher diversity scores, with accurate generation given different control signals.