Unsupervised Object Representation Learning using Translation and Rotation Group Equivariant VAE

• URL: http://arxiv.org/abs/2210.12918v1
• Date: Mon, 24 Oct 2022 02:08:19 GMT
• Title: Unsupervised Object Representation Learning using Translation and Rotation Group Equivariant VAE
• Abstract summary: TARGET-VAE is a translation and rotation group-equivariant variational autoencoder framework. We show that TARGET-VAE learns disentangled representations without supervision that significantly improve upon, and avoid the pathologies of, previous methods. It is able to perform remarkably accurate unsupervised pose and location inference.
• Score: 5.254093731341154
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In many imaging modalities, objects of interest can occur in a variety of locations and poses (i.e. are subject to translations and rotations in 2d or 3d), but the location and pose of an object does not change its semantics (i.e. the object's essence). That is, the specific location and rotation of an airplane in satellite imagery, or the 3d rotation of a chair in a natural image, or the rotation of a particle in a cryo-electron micrograph, do not change the intrinsic nature of those objects. Here, we consider the problem of learning semantic representations of objects that are invariant to pose and location in a fully unsupervised manner. We address shortcomings in previous approaches to this problem by introducing TARGET-VAE, a translation and rotation group-equivariant variational autoencoder framework. TARGET-VAE combines three core innovations: 1) a rotation and translation group-equivariant encoder architecture, 2) a structurally disentangled distribution over latent rotation, translation, and a rotation-translation-invariant semantic object representation, which are jointly inferred by the approximate inference network, and 3) a spatially equivariant generator network. In comprehensive experiments, we show that TARGET-VAE learns disentangled representations without supervision that significantly improve upon, and avoid the pathologies of, previous methods. When trained on images highly corrupted by rotation and translation, the semantic representations learned by TARGET-VAE are similar to those learned on consistently posed objects, dramatically improving clustering in the semantic latent space. Furthermore, TARGET-VAE is able to perform remarkably accurate unsupervised pose and location inference. We expect methods like TARGET-VAE will underpin future approaches for unsupervised object generation, pose prediction, and object detection.

Related papers

• Not All Relations Rotate Alike: Transformation-Aware Decoupling for Viewpoint-Robust 3D Scene Graph Generation [11.312501987929224]
  3D Scene Graph Generation (3DSGG) represents 3D scenes as structured object-relation-object graphs.<n>Current 3DSGG models often fail to produce relation predictions that follow the expected transformation behavior under viewpoint shifts.<n>We propose Transformation-Aware Decoupling (TAD), a viewpoint-robust 3DSGG framework that decouples relation reasoning according to predicate transformation behavior.
  arXiv  Detail & Related papers  (2026-06-25T14:44:40Z)
• Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models [79.96917782423219]
  Orient Anything is the first expert and foundational model designed to estimate object orientation in a single image. By developing a pipeline to annotate the front face of 3D objects, we collect 2M images with precise orientation annotations. Our model achieves state-of-the-art orientation estimation accuracy in both rendered and real images.
  arXiv  Detail & Related papers  (2024-12-24T18:58:43Z)
• Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
  Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries. We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images. Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
  arXiv  Detail & Related papers  (2024-07-26T06:29:09Z)
• Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection [37.142470149311904]
  We propose atemporal equivariant learning framework by considering both spatial and temporal augmentations jointly. We show our pre-training method for 3D object detection which outperforms existing equivariant and invariant approaches in many settings.
  arXiv  Detail & Related papers  (2024-04-17T20:41:49Z)
• DVMNet++: Rethinking Relative Pose Estimation for Unseen Objects [59.51874686414509]
  Existing approaches typically predict 3D translation utilizing the ground-truth object bounding box and approximate 3D rotation with a large number of discrete hypotheses. We present a Deep Voxel Matching Network (DVMNet++) that computes the relative object pose in a single pass. Our approach delivers more accurate relative pose estimates for novel objects at a lower computational cost compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-03-20T15:41:32Z)
• FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection [28.47314201641291]
  We introduce a Fully Rotation-Equivariant Oriented Object Detector (FRED) Our proposed method delivers comparable performance on DOTA-v1.0 and outperforms by 1.5 mAP on DOTA-v1.5, all while significantly reducing the model parameters to 16%.
  arXiv  Detail & Related papers  (2023-12-22T09:31:43Z)
• Dual Quaternion Rotational and Translational Equivariance in 3D Rigid Motion Modelling [6.130606305848124]
  We propose a dual quaternion representation of rigid motions in the 3D space that jointly describes rotations and translations of point sets. Our approach is translation and rotation equivariant, so it does not suffer from shifts in the data. Models endowed with this formulation outperform previous approaches in a human pose forecasting application.
  arXiv  Detail & Related papers  (2023-10-11T16:06:14Z)
• RelPose++: Recovering 6D Poses from Sparse-view Observations [66.6922660401558]
  We address the task of estimating 6D camera poses from sparse-view image sets (2-8 images) We build on the recent RelPose framework which learns a network that infers distributions over relative rotations over image pairs. Our final system results in large improvements in 6D pose prediction over prior art on both seen and unseen object categories.
  arXiv  Detail & Related papers  (2023-05-08T17:59:58Z)
• PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration [16.75367717130046]
  State-of-the-art models are not robust to rotations, which remains an unknown prior to real applications. We introduce a novel Patch-wise Rotation-invariant network (PaRot) Our disentanglement module extracts high-quality rotation-robust features and the proposed lightweight model achieves competitive results.
  arXiv  Detail & Related papers  (2023-02-06T02:13:51Z)
• Robust Change Detection Based on Neural Descriptor Fields [53.111397800478294]
  We develop an object-level online change detection approach that is robust to partially overlapping observations and noisy localization results. By associating objects via shape code similarity and comparing local object-neighbor spatial layout, our proposed approach demonstrates robustness to low observation overlap and localization noises.
  arXiv  Detail & Related papers  (2022-08-01T17:45:36Z)
• Object Scene Representation Transformer [56.40544849442227]
  We introduce Object Scene Representation Transformer (OSRT), a 3D-centric model in which individual object representations naturally emerge through novel view synthesis. OSRT scales to significantly more complex scenes with larger diversity of objects and backgrounds than existing methods. It is multiple orders of magnitude faster at compositional rendering thanks to its light field parametrization and the novel Slot Mixer decoder.
  arXiv  Detail & Related papers  (2022-06-14T15:40:47Z)
• Rotationally Equivariant 3D Object Detection [36.16978685382616]
  We consider the object detection problem in 3D scenes, where an object bounding box should be equivariant regarding the object pose, independent of the scene motion. To incorporate object-level rotation equivariance into 3D object detectors, we need a mechanism to extract equivariant features with local object-level spatial support. Our experiments on both indoor scene and autonomous driving datasets show that significant improvements are obtained by plugging our EON design into existing state-of-the-art 3D object detectors.
  arXiv  Detail & Related papers  (2022-04-28T16:48:50Z)
• Progressive Coordinate Transforms for Monocular 3D Object Detection [52.00071336733109]
  We propose a novel and lightweight approach, dubbed em Progressive Coordinate Transforms (PCT) to facilitate learning coordinate representations. In this paper, we propose a novel and lightweight approach, dubbed em Progressive Coordinate Transforms (PCT) to facilitate learning coordinate representations.
  arXiv  Detail & Related papers  (2021-08-12T15:22:33Z)
• Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes [86.2129580231191]
  Adjoint Rigid Transform (ART) Network is a neural module which can be integrated with a variety of 3D networks. ART learns to rotate input shapes to a learned canonical orientation, which is crucial for a lot of tasks. We will release our code and pre-trained models for further research.
  arXiv  Detail & Related papers  (2021-02-01T20:58:45Z)

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.