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

• URL: http://arxiv.org/abs/2603.18282v2
• Date: Fri, 20 Mar 2026 11:03:34 GMT
• Title: CycleCap: Improving VLMs Captioning Performance via Self-Supervised Cycle Consistency Fine-Tuning
• Abstract summary: Visual-Language Models (VLMs) have achieved remarkable progress in image captioning, visual question answering, and visual reasoning.<n>They remain prone to vision-language misalignment, often producing overly generic or hallucinated descriptions.<n>Existing approaches address this via instruction tuning-requiring costly, large-scale annotated datasets or via complex test-time frameworks for caption refinement.<n>In this work, we revisit image-text alignment through the lens of cycle consistency.
• Score: 65.10059440725041
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment [87.69757277913577]
  We propose TEVI, a framework that uses captions as a signal for what to retain from image embeddings.<n>In a controlled setup with synthetic captions, we show that TEVI is effective at preserving caption-described attributes while discarding others.
  arXiv  Detail & Related papers  (2026-06-05T16:54:40Z)
• Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences [23.022496443851235]
  Given an image and generated text, we map the text back to image space using a text-to-image model and compute the similarity between the original image and its reconstruction.<n>We use the cycle consistency score to rank candidates and construct a preference dataset of 866K comparison pairs.<n>The reward model trained on our dataset, CycleReward, outperforms state-of-the-art alignment metrics on detailed captioning.
  arXiv  Detail & Related papers  (2025-06-02T17:42:58Z)
• RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction [22.72702783743817]
  RICO is a novel framework that refines captions through visual reconstruction.<n>We introduce RICO-Flash, which learns to generate captions like RICO using DPO.<n>Our approach significantly improves caption accuracy and completeness, outperforms most baselines by approximately 10% on CapsBench and CompreCap.
  arXiv  Detail & Related papers  (2025-05-28T17:29:34Z)
• Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioning [70.98890307376548]
  We propose a novel Patch-wise Cross-modal feature Mix-up (PCM) mechanism to adaptively mitigate the unfaithful contents during training.<n>Our PCM-Net ranks first in both in-domain and cross-domain zero-shot image captioning.
  arXiv  Detail & Related papers  (2024-12-31T13:39:08Z)
• CLIP-SCGI: Synthesized Caption-Guided Inversion for Person Re-Identification [9.996589403019675]
  Person re-identification (ReID) has recently benefited from large pretrained vision-language models such as Contrastive Language-Image Pre-Training (CLIP) We propose one straightforward solution by leveraging existing image captioning models to generate pseudo captions for person images. We introduce CLIP-SCGI, a framework that leverages synthesized captions to guide the learning of discriminative and robust representations.
  arXiv  Detail & Related papers  (2024-10-12T06:24:33Z)
• Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval [43.47770490199544]
  Composed Image Retrieval (CIR) is a complex task that retrieves images using a query, which is configured with an image and a caption. We introduce a novel ZS-CIR method that uses Spherical Linear Interpolation (Slerp) to directly merge image and text representations. We also introduce Text-Anchored-Tuning (TAT), a method that fine-tunes the image encoder while keeping the text encoder fixed.
  arXiv  Detail & Related papers  (2024-05-01T15:19:54Z)
• COSA: Concatenated Sample Pretrained Vision-Language Foundation Model [78.32081709802873]
  Most vision-language foundation models employ image-text datasets for pretraining. We propose COSA, a COncatenated SAmple pretrained vision-language foundation model. We achieve this by sequentially concatenating multiple image-text pairs as inputs for pretraining. This transformation effectively converts existing image-text corpora into a pseudo long-form video-paragraph corpus.
  arXiv  Detail & Related papers  (2023-06-15T12:29:42Z)
• Prompt-based Learning for Unpaired Image Captioning [86.44188293709307]
  Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Recent successes of Vision-Language Pre-Trained Models (VL-PTMs) have triggered the development of prompt-based learning. We present in this paper a novel scheme based on prompt to train the UIC model, making best use of the powerful generalization ability.
  arXiv  Detail & Related papers  (2022-05-26T03:13:43Z)
• Enhanced Modality Transition for Image Captioning [51.72997126838352]
  We build a Modality Transition Module (MTM) to transfer visual features into semantic representations before forwarding them to the language model. During the training phase, the modality transition network is optimised by the proposed modality loss. Experiments have been conducted on the MS-COCO dataset demonstrating the effectiveness of the proposed framework.
  arXiv  Detail & Related papers  (2021-02-23T07:20:12Z)
• XGPT: Cross-modal Generative Pre-Training for Image Captioning [80.26456233277435]
  XGPT is a new method of Cross-modal Generative Pre-Training for Image Captioning. It is designed to pre-train text-to-image caption generators through three novel generation tasks. XGPT can be fine-tuned without any task-specific architecture modifications.
  arXiv  Detail & Related papers  (2020-03-03T12:13:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.