Optical Flow boosts Unsupervised Localization and Segmentation

• URL: http://arxiv.org/abs/2307.13640v1
• Date: Tue, 25 Jul 2023 16:45:35 GMT
• Title: Optical Flow boosts Unsupervised Localization and Segmentation
• Authors: Xinyu Zhang, Abdeslam Boularias
• Abstract summary: We propose a new loss term formulation that uses optical flow in unlabeled videos to encourage self-supervised ViT features to become closer to each other. We use the proposed loss function to finetune vision transformers that were originally trained on static images.
• Score: 22.625511865323183
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unsupervised localization and segmentation are long-standing robot vision challenges that describe the critical ability for an autonomous robot to learn to decompose images into individual objects without labeled data. These tasks are important because of the limited availability of dense image manual annotation and the promising vision of adapting to an evolving set of object categories in lifelong learning. Most recent methods focus on using visual appearance continuity as object cues by spatially clustering features obtained from self-supervised vision transformers (ViT). In this work, we leverage motion cues, inspired by the common fate principle that pixels that share similar movements tend to belong to the same object. We propose a new loss term formulation that uses optical flow in unlabeled videos to encourage self-supervised ViT features to become closer to each other if their corresponding spatial locations share similar movements, and vice versa. We use the proposed loss function to finetune vision transformers that were originally trained on static images. Our fine-tuning procedure outperforms state-of-the-art techniques for unsupervised semantic segmentation through linear probing, without the use of any labeled data. This procedure also demonstrates increased performance over original ViT networks across unsupervised object localization and semantic segmentation benchmarks.

Related papers

• Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation [76.68301884987348]
  We propose a simple yet effective approach for self-supervised video object segmentation (VOS) Our key insight is that the inherent structural dependencies present in DINO-pretrained Transformers can be leveraged to establish robust-temporal segmentation correspondences in videos. Our method demonstrates state-of-the-art performance across multiple unsupervised VOS benchmarks and excels in complex real-world multi-object video segmentation tasks.
  arXiv  Detail & Related papers  (2023-11-29T18:47:17Z)
• Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization [31.039698757869974]
  Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Previous CNN-based methods suffer from partial activation issues, concentrating on the object's discriminative part instead of the entire entity scope. We propose a novel Semantic-Constraint Matching Network (SCMN) via a transformer to converge on the divergent activation.
  arXiv  Detail & Related papers  (2023-09-04T03:20:31Z)
• LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training [13.985488693082981]
  We propose a self-supervised object discovery approach that leverages motion and appearance information to produce high-quality object segmentation masks. We demonstrate the effectiveness of our approach, named LOCATE, on multiple standard video object segmentation, image saliency detection, and object segmentation benchmarks.
  arXiv  Detail & Related papers  (2023-08-22T07:27:09Z)
• A Cross-Scale Hierarchical Transformer with Correspondence-Augmented Attention for inferring Bird's-Eye-View Semantic Segmentation [13.013635162859108]
  Inferring BEV semantic segmentation conditioned on multi-camera-view images is a popular scheme in the community as cheap devices and real-time processing. We propose a novel cross-scale hierarchical Transformer with correspondence-augmented attention for semantic segmentation inferring. Our method has state-of-the-art performance in inferring BEV semantic segmentation conditioned on multi-camera-view images.
  arXiv  Detail & Related papers  (2023-04-07T13:52:47Z)
• Location-Aware Self-Supervised Transformers [74.76585889813207]
  We propose to pretrain networks for semantic segmentation by predicting the relative location of image parts. We control the difficulty of the task by masking a subset of the reference patch features visible to those of the query. Our experiments show that this location-aware pretraining leads to representations that transfer competitively to several challenging semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2022-12-05T16:24:29Z)
• Unsupervised Segmentation in Real-World Images via Spelke Object Inference [44.79376336842088]
  Excitatory-Inhibitory Segment Extraction Network (EISEN) learns from optical flow estimates to extract pairwise affinity graphs for static scenes. We show that EISEN achieves a substantial improvement in the state of the art for self-supervised segmentation on challenging synthetic and real-world robotic image datasets.
  arXiv  Detail & Related papers  (2022-05-17T17:39:24Z)
• PreViTS: Contrastive Pretraining with Video Tracking Supervision [53.73237606312024]
  PreViTS is an unsupervised SSL framework for selecting clips containing the same object. PreViTS spatially constrains the frame regions to learn from and trains the model to locate meaningful objects. We train a momentum contrastive (MoCo) encoder on VGG-Sound and Kinetics-400 datasets with PreViTS.
  arXiv  Detail & Related papers  (2021-12-01T19:49:57Z)
• The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos [59.12750806239545]
  We show that a video has different views of the same scene related by moving components, and the right region segmentation and region flow would allow mutual view synthesis. Our model starts with two separate pathways: an appearance pathway that outputs feature-based region segmentation for a single image, and a motion pathway that outputs motion features for a pair of images. By training the model to minimize view synthesis errors based on segment flow, our appearance and motion pathways learn region segmentation and flow estimation automatically without building them up from low-level edges or optical flows respectively.
  arXiv  Detail & Related papers  (2021-11-11T18:59:11Z)
• Intriguing Properties of Vision Transformers [114.28522466830374]
  Vision transformers (ViT) have demonstrated impressive performance across various machine vision problems. We systematically study this question via an extensive set of experiments and comparisons with a high-performing convolutional neural network (CNN) We show effective features of ViTs are due to flexible receptive and dynamic fields possible via the self-attention mechanism.
  arXiv  Detail & Related papers  (2021-05-21T17:59:18Z)
• DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping [72.84991726271024]
  We describe an unsupervised method to detect and segment portions of images of live scenes that are seen moving as a coherent whole. Our method first partitions the motion field by minimizing the mutual information between segments. It uses the segments to learn object models that can be used for detection in a static image.
  arXiv  Detail & Related papers  (2020-08-16T22:05:13Z)

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.