Vector-Quantized Vision Foundation Models for Object-Centric Learning

• URL: http://arxiv.org/abs/2502.20263v6
• Date: Sun, 09 Nov 2025 11:38:43 GMT
• Title: Vector-Quantized Vision Foundation Models for Object-Centric Learning
• Authors: Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni Pajarinen,
• Abstract summary: We propose a unified architecture, Vector-Quantized VFMs for Object-Centric Learning (OCL)<n>The key to our unification is simply shared quantizing VFM representations in OCL aggregation and decoding.<n>Our VVO consistently outperforms baselines in object discovery and recognition, as well as downstream visual prediction and reasoning.
• Score: 29.417271736114454
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Object-Centric Learning (OCL) aggregates image or video feature maps into object-level feature vectors, termed \textit{slots}. It's self-supervision of reconstructing the input from slots struggles with complex object textures, thus Vision Foundation Model (VFM) representations are used as the aggregation input and reconstruction target. Existing methods leverage VFM representations in diverse ways yet fail to fully exploit their potential. In response, we propose a unified architecture, Vector-Quantized VFMs for OCL (VQ-VFM-OCL, or VVO). The key to our unification is simply shared quantizing VFM representations in OCL aggregation and decoding. Experiments show that across different VFMs, aggregators and decoders, our VVO consistently outperforms baselines in object discovery and recognition, as well as downstream visual prediction and reasoning. We also mathematically analyze why VFM representations facilitate OCL aggregation and why their shared quantization as reconstruction targets strengthens OCL supervision. Our source code and model checkpoints are available on https://github.com/Genera1Z/VQ-VFM-OCL.

Related papers

• Evaluating Object-Centric Models beyond Object Discovery [19.133368391349393]
  Object-centric learning (OCL) aims to learn structured scene representations that support compositional generalization and robustness to out-of-distribution data.<n>Most prior work focuses on evaluating OCL models solely through object discovery and simple reasoning tasks.<n>We introduce a unified evaluation task and metric that jointly assess localization (where) and representation usefulness.
  arXiv  Detail & Related papers  (2026-02-07T13:07:48Z)
• From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion [91.35078719566472]
  Vision-Language Models (VLMs) create a severe visual feature bottleneck by using a crude, asymmetric connection.<n>We introduce Cross-Layer Injection (CLI), a novel and lightweight framework that forges a dynamic many-to-many bridge between the two modalities.
  arXiv  Detail & Related papers  (2026-01-15T18:59:10Z)
• Vision-Centric Activation and Coordination for Multimodal Large Language Models [42.26911585599856]
  Multimodal large language models (MLLMs) integrate image features from visual encoders with LLMs, demonstrating advanced comprehension capabilities.<n>However, mainstream MLLMs are solely supervised by the next-token prediction of textual tokens, neglecting critical vision-centric information.<n>We introduce VaCo, which optimize MLLM representations through Vision-Centric activation and Coordination.
  arXiv  Detail & Related papers  (2025-10-16T06:38:39Z)
• FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation [55.01077993490845]
  Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling.<n>We introduce FOCUS, a unified LVLM that integrates segmentation-aware perception and controllable object-centric generation within an end-to-end framework.
  arXiv  Detail & Related papers  (2025-06-20T07:46:40Z)
• METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection [25.542175004831844]
  Open-vocabulary video visual relationship detection aims to detect objects and their relationships in videos without being restricted by predefined object or relationship categories.<n>Existing methods leverage the rich semantic knowledge of pre-trained vision-language models such as CLIP to identify novel categories.<n>We propose Mutual EnhancemenT of Objects and Relationships (METOR) to jointly model and mutually enhance object detection and relationship classification in open-vocabulary scenarios.
  arXiv  Detail & Related papers  (2025-05-10T14:45:43Z)
• Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation [24.531539125814877]
  Vision Foundation Models (VFMs) are large-scale, pre-trained models that serve as general-purpose backbones for various computer vision tasks.<n>One way to tackle this limitation is by employing a task-agnostic feature upsampling module that refines VFM features resolution.<n>Our benchmarking experiments show that selecting appropriate upsampling strategies significantly improves VFM features quality.
  arXiv  Detail & Related papers  (2025-05-04T11:59:26Z)
• Are We Done with Object-Centric Learning? [65.67948794110212]
  Object-centric learning (OCL) seeks to learn representations that only encode an object, isolated from other objects or background cues in a scene. With recent sample-efficient segmentation models, we can separate objects in the pixel space and encode them independently. We address the OOD generalization challenge caused by spurious background cues through the lens of OCL.
  arXiv  Detail & Related papers  (2025-04-09T17:59:05Z)
• Unlocking the Capabilities of Vision-Language Models for Generalizable and Explainable Deepfake Detection [18.125287697902813]
  Current vision-language models (VLMs) have demonstrated remarkable capabilities in understanding multimodal data, but their potential remains underexplored for deepfake detection. We present a novel paradigm that unlocksVLMs' potential capabilities through three components.
  arXiv  Detail & Related papers  (2025-03-19T03:20:03Z)
• Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation [61.64052577026623]
  Real-world multi-view datasets are often heterogeneous and imperfect.<n>We propose a novel robust MVL method (namely RML) with simultaneous representation fusion and alignment.<n>Our RML is self-supervised and can also be applied for downstream tasks as a regularization.
  arXiv  Detail & Related papers  (2025-03-06T07:01:08Z)
• Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models [31.34575955517015]
  Finedefics is an MLLM that enhances the model's FGVR capability by incorporating informative attribute descriptions of objects into the training phase. We employ contrastive learning on object-attribute pairs and attribute-category pairs simultaneously and use examples from similar but incorrect categories as hard negatives. Extensive evaluations across multiple popular FGVR datasets demonstrate that Finedefics outperforms existing MLLMs of comparable parameter sizes.
  arXiv  Detail & Related papers  (2025-01-25T08:52:43Z)
• Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation [47.047267066525265]
  We introduce a novel approach that incorporates object-level contextual knowledge within images. Our proposed approach achieves state-of-the-art performance with strong generalizability across diverse datasets.
  arXiv  Detail & Related papers  (2024-11-26T06:34:48Z)
• Grouped Discrete Representation for Object-Centric Learning [18.44580501357929]
  We propose textitGroup Discrete Representation (GDR) for Object-Centric Learning. GDR decomposes features into attributes via organized channel grouping, and composes these attributes into discrete representation via indexes.
  arXiv  Detail & Related papers  (2024-11-04T17:25:10Z)
• Bootstrapping Top-down Information for Self-modulating Slot Attention [29.82550058869251]
  We propose a novel OCL framework incorporating a top-down pathway. This pathway bootstraps the semantics of individual objects and then modulates the model to prioritize features relevant to these semantics. Our framework achieves state-of-the-art performance across multiple synthetic and real-world object-discovery benchmarks.
  arXiv  Detail & Related papers  (2024-11-04T05:00:49Z)
• Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities [30.176918208200604]
  Vision-Language Models (VLMs) have emerged as general purpose tools for addressing a variety of complex computer vision problems. These models have been shown to be highly capable, but also lacking some basic visual understanding skills. This paper sets out to understand the limitations of SoTA VLMs on fundamental visual tasks.
  arXiv  Detail & Related papers  (2024-08-13T08:26:32Z)
• X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs [49.30255148577368]
  X-Former is a lightweight transformer module designed to exploit the complementary strengths of CL and MIM. X-Former first bootstraps vision-language representation learning and multimodal-to-multimodal generative learning from two frozen vision encoders. It further bootstraps vision-to-language generative learning from a frozen LLM to ensure visual features from X-Former can be interpreted by the LLM.
  arXiv  Detail & Related papers  (2024-07-18T18:39:54Z)
• Learning Object-Centric Representation via Reverse Hierarchy Guidance [73.05170419085796]
  Object-Centric Learning (OCL) seeks to enable Neural Networks to identify individual objects in visual scenes. RHGNet introduces a top-down pathway that works in different ways in the training and inference processes. Our model achieves SOTA performance on several commonly used datasets.
  arXiv  Detail & Related papers  (2024-05-17T07:48:27Z)
• Neural Clustering based Visual Representation Learning [61.72646814537163]
  Clustering is one of the most classic approaches in machine learning and data analysis. We propose feature extraction with clustering (FEC), which views feature extraction as a process of selecting representatives from data. FEC alternates between grouping pixels into individual clusters to abstract representatives and updating the deep features of pixels with current representatives.
  arXiv  Detail & Related papers  (2024-03-26T06:04:50Z)
• Open-Vocabulary Camouflaged Object Segmentation [66.94945066779988]
  We introduce a new task, open-vocabulary camouflaged object segmentation (OVCOS) We construct a large-scale complex scene dataset (textbfOVCamo) containing 11,483 hand-selected images with fine annotations and corresponding object classes. By integrating the guidance of class semantic knowledge and the supplement of visual structure cues from the edge and depth information, the proposed method can efficiently capture camouflaged objects.
  arXiv  Detail & Related papers  (2023-11-19T06:00:39Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation [53.4319652364256]
  This paper presents the RefSAM model, which explores the potential of SAM for referring video object segmentation. Our proposed approach adapts the original SAM model to enhance cross-modality learning by employing a lightweight Cross-RValModal. We employ a parameter-efficient tuning strategy to align and fuse the language and vision features effectively.
  arXiv  Detail & Related papers  (2023-07-03T13:21:58Z)
• SegViT: Semantic Segmentation with Plain Vision Transformers [91.50075506561598]
  We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation. We propose the Attention-to-Mask (ATM) module, in which similarity maps between a set of learnable class tokens and the spatial feature maps are transferred to the segmentation masks. Experiments show that our proposed SegVit using the ATM module outperforms its counterparts using the plain ViT backbone.
  arXiv  Detail & Related papers  (2022-10-12T00:30:26Z)
• Segmenting Moving Objects via an Object-Centric Layered Representation [100.26138772664811]
  We introduce an object-centric segmentation model with a depth-ordered layer representation. We introduce a scalable pipeline for generating synthetic training data with multiple objects. We evaluate the model on standard video segmentation benchmarks.
  arXiv  Detail & Related papers  (2022-07-05T17:59:43Z)
• VinVL: Revisiting Visual Representations in Vision-Language Models [96.39332942534368]
  We develop an improved object detection model to provide object-centric representations of images. New visual features significantly improve the performance across all vision language (VL) tasks. We will release the new object detection model to public.
  arXiv  Detail & Related papers  (2021-01-02T23:35:27Z)
• Look-into-Object: Self-supervised Structure Modeling for Object Recognition [71.68524003173219]
  We propose to "look into object" (explicitly yet intrinsically model the object structure) through incorporating self-supervisions. We show the recognition backbone can be substantially enhanced for more robust representation learning. Our approach achieves large performance gain on a number of benchmarks, including generic object recognition (ImageNet) and fine-grained object recognition tasks (CUB, Cars, Aircraft)
  arXiv  Detail & Related papers  (2020-03-31T12:22:51Z)
• Hierarchical Conditional Relation Networks for Video Question Answering [62.1146543269993]
  We introduce a general-purpose reusable neural unit called Conditional Relation Network (CRN) CRN serves as a building block to construct more sophisticated structures for representation and reasoning over video. Our evaluations on well-known datasets achieved new SoTA results, demonstrating the impact of building a general-purpose reasoning unit on complex domains such as VideoQA.
  arXiv  Detail & Related papers  (2020-02-25T07:00:48Z)

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.