CycleCap: Improving VLMs Captioning Performance via Self-Supervised Cycle Consistency Fine-Tuning

Marios Krestenitis; Christos Tzelepis; Konstantinos Ioannidis; Stefanos Vrochidis; Ioannis Kompatsiaris; Georgios Tzimiropoulos; Shaogang Gong; Ioannis Patras

cs.CVMar 18, 2026

CycleCap: Improving VLMs Captioning Performance via Self-Supervised Cycle Consistency Fine-Tuning

Authors: Marios Krestenitis, Christos Tzelepis, Konstantinos Ioannidis, Stefanos Vrochidis, Ioannis Kompatsiaris, Georgios Tzimiropoulos, Shaogang Gong, Ioannis Patras

Organizations: Queen Mary, University of London · Centre for Research and Technology Hellas · City St George’s, University of London

Abstract

Visual-Language Models (VLMs) have achieved remarkable progress in image captioning, visual question answering, and visual reasoning. Yet they remain prone to vision-language misalignment, often producing overly generic or hallucinated descriptions. Existing approaches address this via instruction tuning-requiring costly, large-scale annotated datasets or via complex test-time frameworks for caption refinement. In this work, we revisit image-text alignment through the lens of cycle consistency: given an image and a caption generated by an image-to-text model, the backward mapping through a text-to-image model should reconstruct an image that closely matches the original. In our setup, a VLM serves as the image-to-text component, while a pre-trained text-to-image model closes the loop by reconstructing the image from the generated caption. Building on this, we introduce CycleCap, a fine-tuning scheme to improve image captioning using Group Relative Policy Optimization (GRPO) with a reward based on the similarity between the original and reconstructed images, computed on-the-fly. Unlike previous work that uses cycle consistency loss for preference dataset construction, our method leverages cycle consistency directly as a self-supervised training signal. This enables the use of raw images alone, eliminating the need for curated image-text datasets, while steering the VLM to produce more accurate and grounded text descriptions. Applied to four VLMs ranging from 1B to 7B parameters, CycleCap yields consistent improvements across captioning and hallucination benchmarks, surpassing state-of-the-art methods that rely on supervised cycle consistency training.

Figures & tables

Figure 1: Overview of the CycleCap framework. The Visual-Language Model generates multiple captions $\{y_{i}\}_{i=1}^{n}$ for an image $x$ . Each caption is used by a frozen Image Generation Model to reconstruct an image $x^{\prime}_{i}=G(y_{i})$ , whilst the similarity between $x$ and $G(y_{i})$ is measured to obtain the cycle consistency reward $R_{i}$ , $i=1,\ldots,n$ . These rewards guide fine-tuning of the Visual–Language Model via GRPO to encourage captions that better reflect visual content in a self-supervised manner.

Panel of Figure 2 — Figure 2: Win-rates (%) of (a) CycleCap fine-tuned models versus the corresponding baseline and (b) Qwen2-VL-7B [ 57 ] fine-tuned with different methods versus the baseline for CompreCap [ 41 ] benchmark.

Method	T2I Model	CompreCap	CAPability	CapsBench	MMHal
Baseline (Qwen2-VL-7B)	—	61.73	70.47	74.17	3.85
CyclePref [ 3 ]	SD3	62.03	70.59	74.27	3.95
RICO-Flash [ 58 ]	FLUX.1-dev	62.93	68.83	75.30	3.92
CycleCap (Ours)	SD3	63.06	72.95	76.38	4.02
CycleCap (Ours)	FLUX.1-dev	63.64	73.73	77.25	4.02

Table 2: Comparison of CycleCap with state-of-the-art cycle-consistency-based methods on CompreCap [ 41 ] , CAPability [ 40 ] , CapsBench [ 36 ] , and MMHal [ 52 ] benchmarks, using Qwen2-VL-7B [ 57 ] as baseline. For CompreCap we report here only Unified Score, the analytic table is included in the Appendix.

Metric	Baseline (Qwen2-VL-7B [ 57 ] )	CyclePref [ 3 ] (SD3)	RICO-Flash [ 58 ] (FLUX.1-dev)	CycleCap (Ours) (SD3)	CycleCap (Ours) (FLUX.1-dev)
Obj. Category	73.52	$72.61$	$70.97$	74.17	77.57
Obj. Number	60.67	$60.00$	$57.85$	65.12	65.74
Obj. Color	89.67	$89.33$	$88.64$	90.36	89.94
Spatial Relation	69.11	$67.50$	$68.24$	71.29	71.08
Scene	77.07	$76.36$	$75.56$	78.60	79.06
Camera Angle	38.00	$39.24$	$36.90$	40.20	38.42

Table 3: Comparison of CycleCap with state-of-the-art methods on the CAPability [ 40 ] benchmark, all using Qwen2-VL-7B [ 57 ] as baseline. Bold and underlined values indicate the best and second best results, respectively.

	CompreCap				CAPability	CapsBench	MMHal
Method	Obj	Attr	Rel	Uni
Baseline (Qwen2-VL-7B)	$77.86$	$2.84$	$2.80$	$61.73$	$70.47$	$74.17$	$3.85$
RICO-Flash [ 58 ]	$79.09$	$2.93$	$2.83$	$62.93$	$68.83$	$75.30$	$3.92$
CycleCap (Ours)	$79.32$	$2.91$	$2.86$	$63.06$	73.73	$76.38$	4.02
RICO-Flash [ 58 ] + CycleCap (Ours)	80.59	2.95	2.88	63.85	73.49	77.72	$4.01$

Table 4: Performance of CycleCap applied on top of RICO-Flash [ 58 ] across captioning and hallucination benchmarks, with Qwen2-VL-7B [ 57 ] as the baseline.

	CompreCap				CapsBench	MMHal
Method	Obj	Attr	Rel	Uni
Baseline (Qwen2-VL-2B)	$73.10$	$2.72$	$2.76$	$59.35$	$69.70$	$3.63$
CycleCap w/ LPIPS	$74.21$	$2.68$	$2.80$	$59.70$	$64.05$	$3.49$
CycleCap w/ CLIP	$73.96$	$2.78$	$2.83$	$60.58$	$71.16$	3.94
CycleCap w/ DreamSim	76.94	2.85	2.86	62.09	72.11	$3.71$

Table 5: Effect of different similarity metrics (LPIPS [ 64 ] , CLIP [ 48 ] , DreamSim [ 20 ] ) on CycleCap performance for fine-tuning the baseline Qwen2-VL-2B [ 57 ] .

	CompreCap				CapsBench	MMHal
Method	Obj	Attr	Rel	Uni
Baseline (Qwen2-VL-2B)	$73.10$	$2.72$	$2.76$	$59.35$	$69.70$	$3.63$
CycleCap w/ SD3	76.94	$2.85$	$2.86$	$62.09$	$72.11$	3.71
CycleCap w/ FLUX.1-schnell	$75.96$	2.87	2.89	62.14	72.18	$3.65$

Table 6: Effect of different text-to-image models (SD3 [ 18 ] and FLUX.1-schnell [ 29 ] ) on the proposed CycleCap performance for fine-tuning baseline Qwen2-VL-2B [ 57 ] .

Figure 3: Qualitative comparison of captions generated by the baseline Qwen2-VL-7B [ 57 ] and the proposed CycleCap on samples from the CapsBench [ 36 ] dataset. Newly added information is indicated in bold . Our method produces more detailed, organized, and accurate descriptions compared to the baseline outputs.

Figure 4: Qualitative comparison of image reconstructions with captions generated by SOTA and our method (CycleCap) deployed for Qwen2-VL-7B. The visualization shows that the model fine-tuned with CycleCap captures more structural details and object attributes, leading to reconstructions closer to the original image. The generated captions are provided in the Appendix.

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Category	Parameters
Training	Batch size: 64	Learning rate: $10^{-5}$
Training	Scheduler: Linear	Epochs: 1
LoRA	Rank $r$ : 64	Dropout: 0.05
LoRA	Target modules: all linear projection layers	Vision tower: frozen
GRPO	KL weight $\beta$ : 0.04	Clip value $\varepsilon$ : 0.02
GRPO	Generations $n$ : 8

Appendix

Table A1: CycleCap training parameters.

Figure A1: The designed prompt of the CycleCap framework used to generate image captions during training.

	InternVL3-1B [ 66 ]		Qwen2-VL-2B [ 57 ]		Qwen2.5-VL-3B [ 5 ]		Qwen2-VL-7B [ 57 ]
	Baseline	CycleCap	Baseline	CycleCap	Baseline	CycleCap	Baseline	CycleCap
Avg. Length	152.64	179.80	209.39	202.73	176.06	198.73	384.56	385.23

Appendix

Table A3: Average caption length (in tokens) on the CompreCap [ 41 ] benchmark.

Method	Generations $n$	CompreCap	CAPability	CapsBench
Baseline (Qwen2-VL-7B)	—	61.73	70.47	74.17
CycleCap	2	62.57	72.40	74.24
CycleCap	4	62.58	72.17	76.22
CycleCap	8	63.06	72.95	76.38

Appendix

Table A4: Effect of the number of GRPO generations

n

(captions generated per image) on CycleCap performance on captioning benchmarks CompreCap (Unified Score) [ 41 ] , CAPability [ 40 ] , and CapsBench [ 36 ] .

Figure A2: Effect of the number of GRPO generations $n$ on CycleCap performance vs. relative training cost. We report performance on CompreCap (Unified Score) [ 41 ] , CAPability [ 40 ] , and CapsBench [ 36 ] benchmarks. Relative training cost is normalized with respect to $n=2$ ( $1\times$ ).

Method	CompreCap	CAPability	CapsBench	MMHal
Baseline (Qwen2-VL-7B)	61.73	70.47	74.17	3.85
DPO	61.78	71.11	74.41	3.95
CycleCap (Ours)	62.33	71.89	74.47	4.01

Appendix

Table A5: Controlled comparison between DPO and CycleCap using the sub-sampled CyclePrefDB-I2T [ 3 ] training set with Qwen2-VL-7B [ 57 ] as the base model. Results are reported on CompreCap (Unified Score) [ 41 ] , CAPability [ 40 ] , CapsBench [ 36 ] , and MMHal [ 52 ] benchmarks.

		CompreCap				CAPability	CapsBench	MMHal
Method	T2I Model	Obj	Attr	Rel	Uni
Baseline (Qwen2-VL-7B)	—	77.86	2.84	2.80	61.73	70.47	74.17	3.85
CyclePref [ 3 ]	SD3	77.29	2.85	2.85	62.03	70.59	74.27	3.95
RICO-Flash [ 58 ]	FLUX.1-dev	79.09	2.93	2.83	62.93	68.83	75.30	3.92
CycleCap (Ours)	SD3	79.32	2.91	2.86	63.06	72.95	76.38	4.02
CycleCap (Ours)	FLUX.1-dev	79.67	2.93	2.90	63.64	73.73	77.25	4.02

Appendix

Table A6: Detailed results corresponding to Tab. 2 in the main paper, comparing the proposed CycleCap with SOTA cycle-consistency-based approaches.

Figure A3: Additional qualitative comparisons between captions generated by the baseline Qwen2-VL-7B [ 57 ] model and the CycleCap fine-tuned version, for image samples from the CapsBench [ 36 ] and CompreCap [ 41 ] benchmarks. Newly added information is shown in bold , content present in the baseline but not preserved in the CycleCap caption is underlined , and hallucinations are highlighted in pink. Overall, CycleCap tends to produce more structured and grounded descriptions, while it adds details related to object attributes, spatial layout, and broader scene context.

Figure A4: Generated captions corresponding to the qualitative reconstruction comparison shown in the first row of Fig. 4 in the main paper.

Figure A5: Generated captions corresponding to the qualitative reconstruction comparison shown in the second row of Fig. 4 in the main paper.

Cycle Consistency

See all 13 papers

Re $^3$ Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning
Aug 21, 2026Haonan Jia, Shichao Dong, Zenghui Sun +7Image Captioning RL for VLMs
Taobao & Tmall Group of Alibaba · The Hong Kong University of Science and Technology (Guangzhou) · Shanghai Artificial Intelligence Laboratory
Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning
Mar 2, 2026Haonan Jia, Shichao Dong, Xin Dong +6Image Captioning Modality Gap in VLMs
Taobao & Tmall Group of Alibaba · The University of Hong Kong
CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning
Jun 8, 2026Penghui Yang, Long Xing, Xiaoyi Dong +10Image Captioning Multimodal Pretraining
Tsinghua University · University of Science and Technology of China · Microsoft +4

Aug 21, 2026J/K move · Enter open · S save

Re $^3$ Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning

Haonan Jia, Shichao Dong, Zenghui Sun, Jiawen Zheng+6

Taobao & Tmall Group of Alibaba · The Hong Kong University of Science and Technology (Guangzhou) · Shanghai Artificial Intelligence Laboratory

Image Captioning RL for VLMs

Open paper AskPDF arXiv

Reinforcement Learning (RL) has demonstrated significant gains in image captioning, yet it is still limited in encouraging Large Vision-Language Models (LVLMs) to explore novel reasoning strategies. This limitation leads to a performance gap between RL and Supervised Fine-Tuning (SFT). In this paper, we argue that multi-modal retrieval can serve as an effective reasoning signal for caption refinement. Based on this insight, we present the Retrieval-Guided Refinement for Image Captioning (Re

^3

Cap), a retrieval-guided reasoning strategy that enhances image captioning without requiring additional annotations. Instantiated by Caption Refinement Suggester (CRS) and Caption Quality Assessor (CQA), this strategy identifies hallucinations and omissions in image captions, leading to more accurate and detailed descriptions. Extensive experiments demonstrate the superiority of our method in image captioning, even compared with Supervised Fine-Tuning. Especially, Re

^3

Cap outperforms GRPO with an average improvement of 8.64% in relation reasoning on the COCO-LN500 benchmark.

Abstract

Cycle Consistency

Explore similar work

Re3^33Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning

Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning

CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning

Re $^3$ Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning