CL-CLIP: CLIP-Based Continual Learning Framework with Cost-Volume Category Decoupling for Object Detection

• URL: http://arxiv.org/abs/2606.06978v1
• Date: Fri, 05 Jun 2026 07:09:52 GMT
• Title: CL-CLIP: CLIP-Based Continual Learning Framework with Cost-Volume Category Decoupling for Object Detection
• Abstract summary: Continual Object Detection (COD) requires a detector to acquire new categories over time while preserving previously learned ones.<n>Recent CLIP-based open-vocabulary detectors have shown strong zero-shot generalization.<n>We propose CL-CLIP, a CLIP-based COD framework that equips open-vocabulary detectors with better continual learning ability.
• Score: 25.86078021755795
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual Object Detection (COD) requires a detector to acquire new categories over time while preserving previously learned ones. This goal is closely related to open-vocabulary detection, since both settings require reasoning over categories that are not fully covered by the annotations available at the current training stage. Recent CLIP-based open-vocabulary detectors have shown strong zero-shot generalization, and frameworks such as F-ViT demonstrate that vision-language pretraining can provide powerful zero-shot detection ability for unseen categories. However, real-world deployments cannot remain purely zero-shot: once these detectors are continually updated on newly introduced categories, they suffer severe catastrophic forgetting and quickly lose their previously calibrated detection ability. We therefore propose CL-CLIP, a CLIP-based COD framework that equips open-vocabulary detectors with better continual learning ability through cost-volume-guided category decoupling. Specifically, following CAT-Seg, we compute a CLIP image-text similarity cost volume, defined as dense category-wise response maps between visual tokens and class text embeddings. This zero-shot spatial prior decomposes shared region features into class-specific pathways, which are then processed by a Multi-Expert RoI head. Extensive experiments on PASCAL VOC and MS-COCO show that CL-CLIP substantially improves the F-ViT baseline under continual fine-tuning and achieves competitive performance with existing continual object detectors, especially in adapting to newly introduced categories while preserving competitive base-class performance.

Related papers

• CLIP-Joint-Detect: End-to-End Joint Training of Object Detectors with Contrastive Vision-Language Supervision [0.08699280339422537]
  We propose CLIP-Joint-Detect, a framework that integrates CLIP-style contrastive vision-language supervision through end-to-end joint training.<n>A lightweight parallel head projects region or grid features into the CLIP embedding space and aligns them with learnable class-specific text embeddings via InfoNCE contrastive loss and an auxiliary cross-entropy term.<n>We validate it on Pascal VOC 2007+2012 using Faster R-CNN and on the large-scale MS 2017 benchmark using modern YOLO detectors (YOLOv11)
  arXiv  Detail & Related papers  (2025-12-28T15:21:20Z)
• Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation [19.749490092520006]
  Self-Calibrated CLIP (SC-CLIP) is a training-free method that calibrates CLIP to produce finer representations.<n>SC-CLIP boosts the performance of vanilla CLIP ViT-L/14 by 6.8 times.
  arXiv  Detail & Related papers  (2024-11-24T15:14:05Z)
• C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection [98.34703790782254]
  We introduce Category Common Prompt CLIP, which integrates the category common prompt into the text encoder to inject category-related concepts into the image encoder.<n>Our method achieves a 12.41% improvement in detection accuracy compared to the original CLIP, without introducing additional parameters during testing.
  arXiv  Detail & Related papers  (2024-08-19T02:14:25Z)
• CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models [23.398619576886375]
  Continual learning (CL) aims to help deep neural networks learn new knowledge while retaining what has been learned. Our work proposes Continual LeArning with Probabilistic finetuning (CLAP) - a probabilistic modeling framework over visual-guided text features per task.
  arXiv  Detail & Related papers  (2024-03-28T04:15:58Z)
• Open-Vocabulary Segmentation with Semantic-Assisted Calibration [68.41025728960176]
  We study open-vocabulary segmentation (OVS) through calibrating in-vocabulary and domain-biased embedding space with contextual prior of CLIP.<n>We present a Semantic-assisted CAlibration Network (SCAN) to achieve state-of-the-art performance on open-vocabulary segmentation benchmarks.
  arXiv  Detail & Related papers  (2023-12-07T07:00:09Z)
• EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment [28.983503845298824]
  We propose Early Dense Alignment (EDA) to bridge the gap between generalizable local semantics and object-level prediction. In EDA, we use object-level supervision to learn the dense-level rather than object-level alignment to maintain the local fine-grained semantics.
  arXiv  Detail & Related papers  (2023-09-03T12:04:14Z)
• GridCLIP: One-Stage Object Detection by Grid-Level CLIP Representation Learning [55.77244064907146]
  One-stage detector GridCLIP learns grid-level representations to adapt to the intrinsic principle of one-stage detection learning. Experiments show that the learned CLIP-based grid-level representations boost the performance of undersampled (infrequent and novel) categories.
  arXiv  Detail & Related papers  (2023-03-16T12:06:02Z)
• Global Knowledge Calibration for Fast Open-Vocabulary Segmentation [124.74256749281625]
  We introduce a text diversification strategy that generates a set of synonyms for each training category. We also employ a text-guided knowledge distillation method to preserve the generalizable knowledge of CLIP. Our proposed model achieves robust generalization performance across various datasets.
  arXiv  Detail & Related papers  (2023-03-16T09:51:41Z)
• The CLEAR Benchmark: Continual LEArning on Real-World Imagery [77.98377088698984]
  Continual learning (CL) is widely regarded as crucial challenge for lifelong AI. We introduce CLEAR, the first continual image classification benchmark dataset with a natural temporal evolution of visual concepts. We find that a simple unsupervised pre-training step can already boost state-of-the-art CL algorithms.
  arXiv  Detail & Related papers  (2022-01-17T09:09:09Z)
• DenseCLIP: Extract Free Dense Labels from CLIP [130.3830819077699]
  Contrastive Language-Image Pre-training (CLIP) has made a remarkable breakthrough in open-vocabulary zero-shot image recognition. DenseCLIP+ surpasses SOTA transductive zero-shot semantic segmentation methods by large margins. Our finding suggests that DenseCLIP can serve as a new reliable source of supervision for dense prediction tasks.
  arXiv  Detail & Related papers  (2021-12-02T09:23:01Z)

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.