Looking Locally: Object-Centric Vision Transformers as Foundation Models for Efficient Segmentation

• URL: http://arxiv.org/abs/2502.02763v2
• Date: Sat, 05 Jul 2025 12:50:10 GMT
• Title: Looking Locally: Object-Centric Vision Transformers as Foundation Models for Efficient Segmentation
• Authors: Manuel Traub, Martin V. Butz,
• Abstract summary: Current state-of-the-art segmentation models encode entire images before focusing on specific objects.<n>We introduce FLIP, a parameter-efficient vision model that realizes object segmentation through biologically-inspired top-down attention.<n>We show that FLIP segments even very small objects accurately, where existing models fail severely.
• Score: 3.5297361401370053
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current state-of-the-art segmentation models encode entire images before focusing on specific objects. As a result, they waste computational resources - particularly when small objects are to be segmented in high-resolution scenes. We introduce FLIP (Fovea-Like Input Patching), a parameter-efficient vision model that realizes object segmentation through biologically-inspired top-down attention. FLIP selectively samples multi-resolution patches centered on objects of interest from the input. As a result, it allocates high-resolution processing to object centers while maintaining coarser peripheral context. This off-grid, scale-invariant design enables FLIP to outperform META's Segment Anything models (SAM) by large margins: With more than 1000x fewer parameters, FLIP-Tiny (0.51M parameters) reaches a mean IoU of 78.24% while SAM-H reaches 75.41% IoU (641.1M parameters). FLIP-Large even achieves 80.33% mean IoU (96.6M parameters), still running about 6$\times$ faster than SAM-H. We evaluate on six benchmarks in total. In five established benchmarks (Hypersim, KITTI-360, OpenImages, COCO, LVIS) FLIP consistently outperforms SAM and various variants of it. In our novel ObjaScale dataset, which stress-tests scale invariance with objects ranging from 0.0001% up-to 25% of the image area, we show that FLIP segments even very small objects accurately, where existing models fail severely. FLIP opens new possibilities for real-time, object-centric vision applications and offers much higher energy efficiency. We believe that FLIP can act as a powerful foundation model, as it is very well-suited to track objects over time, for example, when being integrated into slot-based scene segmentation architectures.

Related papers

• Efficient Oriented Object Detection with Enhanced Small Object Recognition in Aerial Images [2.9138705529771123]
  We present a novel enhancement to the YOLOv8 model, tailored for oriented object detection tasks.<n>Our model features a wavelet transform-based C2f module for capturing associative features and an Adaptive Scale Feature Pyramid (ASFP) module that leverages P2 layer details.<n>Our approach provides a more efficient architectural design than DecoupleNet, which has 23.3M parameters, all while maintaining detection accuracy.
  arXiv  Detail & Related papers  (2024-12-17T05:45:48Z)
• Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection [12.417754433715903]
  We present FAIM, a new VOD method that enhances temporal Feature Aggregation by leveraging Instance Mask features.<n>Using YOLOX as a base detector, FAIM achieves 87.9% mAP on the ImageNet VID dataset at 33 FPS on a single 2080Ti GPU.
  arXiv  Detail & Related papers  (2024-12-06T10:12:10Z)
• Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models [111.97026994761254]
  Mixture-of-Transformers (MoT) is a sparse multi-modal transformer architecture.<n>MoT decouples non-embedding parameters of the model by modality.<n>We evaluate MoT across multiple settings and model scales.
  arXiv  Detail & Related papers  (2024-11-07T18:59:06Z)
• Bridge the Points: Graph-based Few-shot Segment Anything Semantically [79.1519244940518]
  Recent advancements in pre-training techniques have enhanced the capabilities of vision foundation models. Recent studies extend the SAM to Few-shot Semantic segmentation (FSS) We propose a simple yet effective approach based on graph analysis.
  arXiv  Detail & Related papers  (2024-10-09T15:02:28Z)
• Adapting Segment Anything Model for Unseen Object Instance Segmentation [70.60171342436092]
  Unseen Object Instance (UOIS) is crucial for autonomous robots operating in unstructured environments. We propose UOIS-SAM, a data-efficient solution for the UOIS task. UOIS-SAM integrates two key components: (i) a Heatmap-based Prompt Generator (HPG) to generate class-agnostic point prompts with precise foreground prediction, and (ii) a Hierarchical Discrimination Network (HDNet) that adapts SAM's mask decoder.
  arXiv  Detail & Related papers  (2024-09-23T19:05:50Z)
• FocSAM: Delving Deeply into Focused Objects in Segmenting Anything [58.042354516491024]
  The Segment Anything Model (SAM) marks a notable milestone in segmentation models. We propose FocSAM with a pipeline redesigned on two pivotal aspects. First, we propose Dynamic Window Multi-head Self-Attention (Dwin-MSA) to dynamically refocus SAM's image embeddings on the target object. Second, we propose Pixel-wise Dynamic ReLU (P-DyReLU) to enable sufficient integration of interactive information from a few initial clicks.
  arXiv  Detail & Related papers  (2024-05-29T02:34:13Z)
• MAS-SAM: Segment Any Marine Animal with Aggregated Features [55.91291540810978]
  We propose a novel feature learning framework named MAS-SAM for marine animal segmentation. Our method enables to extract richer marine information from global contextual cues to fine-grained local details.
  arXiv  Detail & Related papers  (2024-04-24T07:38:14Z)
• FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects [55.77542145604758]
  FoundationPose is a unified foundation model for 6D object pose estimation and tracking. Our approach can be instantly applied at test-time to a novel object without fine-tuning.
  arXiv  Detail & Related papers  (2023-12-13T18:28:09Z)
• EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything [36.553867358541154]
  Segment Anything Model (SAM) has emerged as a powerful tool for numerous vision applications. We propose EfficientSAMs, light-weight SAM models that exhibits decent performance with largely reduced complexity. Our idea is based on leveraging masked image pretraining, SAMI, which learns to reconstruct features from SAM image encoder for effective visual representation learning.
  arXiv  Detail & Related papers  (2023-12-01T18:31:00Z)
• SimulFlow: Simultaneously Extracting Feature and Identifying Target for Unsupervised Video Object Segmentation [28.19471998380114]
  Unsupervised video object segmentation (UVOS) aims at detecting the primary objects in a given video sequence without any human interposing. Most existing methods rely on two-stream architectures that separately encode the appearance and motion information before fusing them to identify the target and generate object masks. We propose a novel UVOS model called SimulFlow that simultaneously performs feature extraction and target identification.
  arXiv  Detail & Related papers  (2023-11-30T06:44:44Z)
• Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples [61.66967790884943]
  Referring video object segmentation (RVOS) relies on sufficient data for a given scene. In more realistic scenarios, only minimal annotations are available for a new scene. We propose a model with a newly designed cross-modal affinity (CMA) module based on a Transformer architecture. CMA module builds multimodal affinity with a few samples, thus quickly learning new semantic information, and enabling the model to adapt to different scenarios.
  arXiv  Detail & Related papers  (2023-09-05T08:34:23Z)
• Segment Anything Meets Point Tracking [116.44931239508578]
  This paper presents a novel method for point-centric interactive video segmentation, empowered by SAM and long-term point tracking. We highlight the merits of point-based tracking through direct evaluation on the zero-shot open-world Unidentified Video Objects (UVO) benchmark. Our experiments on popular video object segmentation and multi-object segmentation tracking benchmarks, including DAVIS, YouTube-VOS, and BDD100K, suggest that a point-based segmentation tracker yields better zero-shot performance and efficient interactions.
  arXiv  Detail & Related papers  (2023-07-03T17:58:01Z)
• Real-Time Flying Object Detection with YOLOv8 [0.0]
  This paper presents a generalized model for real-time detection of flying objects. We also present a refined model that achieves state-of-the-art results for flying object detection.
  arXiv  Detail & Related papers  (2023-05-17T06:11:10Z)
• MOSE: A New Dataset for Video Object Segmentation in Complex Scenes [106.64327718262764]
  Video object segmentation (VOS) aims at segmenting a particular object throughout the entire video clip sequence. The state-of-the-art VOS methods have achieved excellent performance (e.g., 90+% J&F) on existing datasets. We collect a new VOS dataset called coMplex video Object SEgmentation (MOSE) to study the tracking and segmenting objects in complex environments.
  arXiv  Detail & Related papers  (2023-02-03T17:20:03Z)
• DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition [62.95223898214866]
  We explore effective Vision Transformers to pursue a preferable trade-off between the computational complexity and size of the attended receptive field. With a pyramid architecture, we construct a Multi-Scale Dilated Transformer (DilateFormer) by stacking MSDA blocks at low-level stages and global multi-head self-attention blocks at high-level stages. Our experiment results show that our DilateFormer achieves state-of-the-art performance on various vision tasks.
  arXiv  Detail & Related papers  (2023-02-03T14:59:31Z)
• Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation [99.70336991366403]
  We propose a concise, practical, and efficient architecture for appearance and motion feature alignment. The proposed HFAN reaches a new state-of-the-art performance on DAVIS-16, achieving 88.7 $mathcalJ&mathcalF$ Mean, i.e., a relative improvement of 3.5% over the best published result.
  arXiv  Detail & Related papers  (2022-07-18T10:10:14Z)
• Global Context Vision Transformers [78.5346173956383]
  We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. We address the lack of the inductive bias in ViTs, and propose to leverage a modified fused inverted residual blocks in our architecture. Our proposed GC ViT achieves state-of-the-art results across image classification, object detection and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2022-06-20T18:42:44Z)
• EOLO: Embedded Object Segmentation only Look Once [0.0]
  We introduce an anchor-free and single-shot instance segmentation method, which is conceptually simple with 3 independent branches, fully convolutional and can be used by easily embedding it into mobile and embedded devices. Our method, refer as EOLO, reformulates the instance segmentation problem as predicting semantic segmentation and distinguishing overlapping objects problem, through instance center classification and 4D distance regression on each pixel. Without any bells and whistles, EOLO achieves 27.7$%$ in mask mAP under IoU50 and reaches 30 FPS on 1080Ti GPU, with a single-model and single-scale training/testing on
  arXiv  Detail & Related papers  (2020-03-31T21:22:05Z)

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.