Space-Time Correspondence as a Contrastive Random Walk

• URL: http://arxiv.org/abs/2006.14613v2
• Date: Thu, 3 Dec 2020 18:59:03 GMT
• Title: Space-Time Correspondence as a Contrastive Random Walk
• Authors: Allan Jabri, Andrew Owens, Alexei A. Efros
• Abstract summary: We cast correspondence as prediction of links in a space-time graph constructed from video. We learn a representation in which pairwise similarity defines transition probability of a random walk. We demonstrate that a technique we call edge dropout, as well as self-supervised adaptation at test-time, further improve transfer for object-centric correspondence.
• Score: 47.40711876423659
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper proposes a simple self-supervised approach for learning a representation for visual correspondence from raw video. We cast correspondence as prediction of links in a space-time graph constructed from video. In this graph, the nodes are patches sampled from each frame, and nodes adjacent in time can share a directed edge. We learn a representation in which pairwise similarity defines transition probability of a random walk, so that long-range correspondence is computed as a walk along the graph. We optimize the representation to place high probability along paths of similarity. Targets for learning are formed without supervision, by cycle-consistency: the objective is to maximize the likelihood of returning to the initial node when walking along a graph constructed from a palindrome of frames. Thus, a single path-level constraint implicitly supervises chains of intermediate comparisons. When used as a similarity metric without adaptation, the learned representation outperforms the self-supervised state-of-the-art on label propagation tasks involving objects, semantic parts, and pose. Moreover, we demonstrate that a technique we call edge dropout, as well as self-supervised adaptation at test-time, further improve transfer for object-centric correspondence.

Related papers

• Entropy Neural Estimation for Graph Contrastive Learning [9.032721248598088]
  Contrastive learning on graphs aims at extracting distinguishable high-level representations of nodes. We propose a simple yet effective subset sampling strategy to contrast pairwise representations between views of a dataset. We conduct extensive experiments on seven graph benchmarks, and the proposed approach achieves competitive performance.
  arXiv  Detail & Related papers  (2023-07-26T03:55:08Z)
• Line Graph Contrastive Learning for Link Prediction [4.876567687745239]
  We propose a Line Graph Contrastive Learning (LGCL) method to obtain multiview information. With experiments on six public datasets, LGCL outperforms current benchmarks on link prediction tasks.
  arXiv  Detail & Related papers  (2022-10-25T06:57:00Z)
• Generative Subgraph Contrast for Self-Supervised Graph Representation Learning [16.374143635724327]
  We propose a novel adaptive subgraph generation based contrastive learning framework for efficient and robust self-supervised graph representation learning. It aims to generate contrastive samples by capturing the intrinsic structures of the graph and distinguish the samples based on the features and structures of subgraphs simultaneously.
  arXiv  Detail & Related papers  (2022-07-25T09:08:46Z)
• REGTR: End-to-end Point Cloud Correspondences with Transformers [79.52112840465558]
  We conjecture that attention mechanisms can replace the role of explicit feature matching and RANSAC. We propose an end-to-end framework to directly predict the final set of correspondences. Our approach achieves state-of-the-art performance on 3DMatch and ModelNet benchmarks.
  arXiv  Detail & Related papers  (2022-03-28T06:01:00Z)
• Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences [118.6018141306409]
  We propose Probabilistic Warp Consistency, a weakly-supervised learning objective for semantic matching. We first construct an image triplet by applying a known warp to one of the images in a pair depicting different instances of the same object class. Our objective also brings substantial improvements in the strongly-supervised regime, when combined with keypoint annotations.
  arXiv  Detail & Related papers  (2022-03-08T18:55:11Z)
• Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases [131.50372468579067]
  We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. We represent the reconstructed surfaces as atlases computed by a neural network, which enables us to establish correspondences between frames. Our approach outperforms state-of-the-art ones on several challenging datasets.
  arXiv  Detail & Related papers  (2021-11-12T17:48:25Z)
• Modelling Neighbor Relation in Joint Space-Time Graph for Video Correspondence Learning [53.74240452117145]
  This paper presents a self-supervised method for learning reliable visual correspondence from unlabeled videos. We formulate the correspondence as finding paths in a joint space-time graph, where nodes are grid patches sampled from frames, and are linked by two types of edges. Our learned representation outperforms the state-of-the-art self-supervised methods on a variety of visual tasks.
  arXiv  Detail & Related papers  (2021-09-28T05:40:01Z)
• Towards Efficient Scene Understanding via Squeeze Reasoning [71.1139549949694]
  We propose a novel framework called Squeeze Reasoning. Instead of propagating information on the spatial map, we first learn to squeeze the input feature into a channel-wise global vector. We show that our approach can be modularized as an end-to-end trained block and can be easily plugged into existing networks.
  arXiv  Detail & Related papers  (2020-11-06T12:17:01Z)

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.