WRF4CIR: Weight-Regularized Fine-Tuning Network for Composed Image Retrieval

• URL: http://arxiv.org/abs/2604.05583v1
• Date: Tue, 07 Apr 2026 08:23:39 GMT
• Title: WRF4CIR: Weight-Regularized Fine-Tuning Network for Composed Image Retrieval
• Abstract summary: Composed Image Retrieval (CIR) task aims to retrieve target images based on reference images and modification texts.<n>Current CIR methods rely on fine-tuning vision-language pre-trained models.<n>We introduce WRF4CIR, a Weight-Regularized Fine-tuning network for CIR.
• Score: 58.85945491755373
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Composed Image Retrieval (CIR) task aims to retrieve target images based on reference images and modification texts. Current CIR methods primarily rely on fine-tuning vision-language pre-trained models. However, we find that these approaches commonly suffer from severe overfitting, posing challenges for CIR with limited triplet data. To better understand this issue, we present a systematic study of overfitting in VLP-based CIR, revealing a significant and previously overlooked generalization gap across different models and datasets. Motivated by these findings, we introduce WRF4CIR, a Weight-Regularized Fine-tuning network for CIR. Specifically, during the fine-tuning process, we apply adversarial perturbations to the model weights for regularization, where these perturbations are generated in the opposite direction of gradient descent. Intuitively, WRF4CIR increases the difficulty of fitting the training data, which helps mitigate overfitting in CIR under limited triplet supervision. Extensive experiments on benchmark datasets demonstrate that WRF4CIR significantly narrows the generalization gap and achieves substantial improvements over existing methods.

Related papers

• FBCIR: Balancing Cross-Modal Focuses in Composed Image Retrieval [12.652218923459742]
  Composed image retrieval (CIR) requires multi-modal models to jointly reason over visual content and semantic modifications presented in text-image input pairs.<n>We propose FBCIR, a multi-modal focus interpretation method that identifies the most crucial visual and textual input components to a model's retrieval decisions.
  arXiv  Detail & Related papers  (2026-03-12T04:05:27Z)
• Implicit Neural Representation-Based Continuous Single Image Super Resolution: An Empirical Study [50.15623093332659]
  Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR)<n>We compare existing techniques across diverse settings and present aggregated performance results on multiple image quality metrics.<n>We examine a new loss function that penalizes intensity variations while preserving edges, textures, and finer details during training.
  arXiv  Detail & Related papers  (2026-01-25T07:09:20Z)
• Rotation Equivariant Arbitrary-scale Image Super-Resolution [62.41329042683779]
  The arbitrary-scale image super-resolution (ASISR) aims to achieve arbitrary-scale high-resolution recoveries from a low-resolution input image.<n>We make efforts to construct a rotation equivariant ASISR method in this study.
  arXiv  Detail & Related papers  (2025-08-07T08:51:03Z)
• CoLLM: A Large Language Model for Composed Image Retrieval [76.29725148964368]
  Composed Image Retrieval (CIR) is a complex task that aims to retrieve images based on a multimodal query.<n>We present CoLLM, a one-stop framework that generates triplets on-the-fly from image-caption pairs.<n>We leverage Large Language Models (LLMs) to generate joint embeddings of reference images and modification texts.
  arXiv  Detail & Related papers  (2025-03-25T17:59:50Z)
• Generalizable Non-Line-of-Sight Imaging with Learnable Physical Priors [52.195637608631955]
  Non-line-of-sight (NLOS) imaging has attracted increasing attention due to its potential applications. Existing NLOS reconstruction approaches are constrained by the reliance on empirical physical priors. We introduce a novel learning-based solution, comprising two key designs: Learnable Path Compensation (LPC) and Adaptive Phasor Field (APF)
  arXiv  Detail & Related papers  (2024-09-21T04:39:45Z)
• Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection [22.60228799622782]
  Key bottleneck in object detection in IR images is lack of sufficient labeled training data. We seek to leverage cues from the RGB modality to scale object detectors to the IR modality, while preserving model performance in the RGB modality. We first pretrain these factor matrices on the RGB modality, for which plenty of training data are assumed to exist and then augment only a few trainable parameters for training on the IR modality to avoid over-fitting.
  arXiv  Detail & Related papers  (2023-09-28T16:55:52Z)
• Blind Super-Resolution for Remote Sensing Images via Conditional Stochastic Normalizing Flows [14.882417028542855]
  We propose a novel blind SR framework based on the normalizing flow (BlindSRSNF) to address the above problems. BlindSRSNF learns the conditional probability distribution over the high-resolution image space given a low-resolution (LR) image by explicitly optimizing the variational bound on the likelihood. We show that the proposed algorithm can obtain SR results with excellent visual perception quality on both simulated LR and real-world RSIs.
  arXiv  Detail & Related papers  (2022-10-14T12:37:32Z)
• Universal adversarial perturbation for remote sensing images [41.54094422831997]
  This paper proposes a novel method combining an encoder-decoder network with an attention mechanism to verify that UAP makes the RSI classification model error classification. The experimental results show that the UAP can make the RSI misclassify, and the attack success rate (ASR) of our proposed method on the RSI data set is as high as 97.35%.
  arXiv  Detail & Related papers  (2022-02-22T06:43:28Z)
• When Relation Networks meet GANs: Relation GANs with Triplet Loss [110.7572918636599]
  Training stability is still a lingering concern of generative adversarial networks (GANs) In this paper, we explore a relation network architecture for the discriminator and design a triplet loss which performs better generalization and stability. Experiments on benchmark datasets show that the proposed relation discriminator and new loss can provide significant improvement on variable vision tasks.
  arXiv  Detail & Related papers  (2020-02-24T11:35:28Z)

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.