Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias

• URL: http://arxiv.org/abs/2101.07296v1
• Date: Mon, 18 Jan 2021 19:29:41 GMT
• Title: Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias
• Authors: Stefan Stojanov, Anh Thai, James M. Rehg
• Abstract summary: We investigate how reasoning about 3D shape can be used to improve low-shot learning methods' generalization performance. We propose a new way to improve existing low-shot learning approaches by learning a discriminative embedding space using 3D object shape. We also develop Toys4K, a new 3D object dataset with the biggest number of object categories that can also support low-shot learning.
• Score: 22.863686803150625
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It is widely accepted that reasoning about object shape is important for object recognition. However, the most powerful object recognition methods today do not explicitly make use of object shape during learning. In this work, motivated by recent developments in low-shot learning, findings in developmental psychology, and the increased use of synthetic data in computer vision research, we investigate how reasoning about 3D shape can be used to improve low-shot learning methods' generalization performance. We propose a new way to improve existing low-shot learning approaches by learning a discriminative embedding space using 3D object shape, and utilizing this embedding by learning how to map images into it. Our new approach improves the performance of image-only low-shot learning approaches on multiple datasets. We also develop Toys4K, a new 3D object dataset with the biggest number of object categories that can also support low-shot learning.

Related papers

• 3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation [4.415086501328683]
  We deal with the problem in a reasonable new setting, namely 3D shape is exploited in the training process, and the testing is still purely image-based. We propose a novel contrastive knowledge distillation framework that effectively transfers 3D-augmented image representation from a multi-modal model to an image-based model. We experimentally report state-of-the-art results compared with existing category-agnostic image-based methods by a large margin.
  arXiv  Detail & Related papers  (2022-06-02T16:46:18Z)
• End-to-End Learning of Multi-category 3D Pose and Shape Estimation [128.881857704338]
  We propose an end-to-end method that simultaneously detects 2D keypoints from an image and lifts them to 3D. The proposed method learns both 2D detection and 3D lifting only from 2D keypoints annotations. In addition to being end-to-end in image to 3D learning, our method also handles objects from multiple categories using a single neural network.
  arXiv  Detail & Related papers  (2021-12-19T17:10:40Z)
• RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection [138.2892824662943]
  A promising solution is to make better use of the synthetic dataset, which consists of CAD object models, to boost the learning on real datasets. Recent work on 3D pre-training exhibits failure when transfer features learned on synthetic objects to other real-world applications. In this work, we put forward a new method called RandomRooms to accomplish this objective.
  arXiv  Detail & Related papers  (2021-08-17T17:56:12Z)
• Learning without Forgetting for 3D Point Cloud Objects [7.761414660999872]
  When we fine-tune a well-trained deep learning model for a new set of classes, the network learns new concepts but gradually forgets the knowledge of old training. We investigate knowledge distillation techniques on 3D data to reduce catastrophic forgetting of the previous training. We observe that exploring the interrelation of old and new knowledge during training helps to learn new concepts without forgetting old ones.
  arXiv  Detail & Related papers  (2021-06-27T16:39:39Z)
• Neural Articulated Radiance Field [90.91714894044253]
  We present Neural Articulated Radiance Field (NARF), a novel deformable 3D representation for articulated objects learned from images. Experiments show that the proposed method is efficient and can generalize well to novel poses.
  arXiv  Detail & Related papers  (2021-04-07T13:23:14Z)
• Unsupervised Learning of 3D Object Categories from Videos in the Wild [75.09720013151247]
  We focus on learning a model from multiple views of a large collection of object instances. We propose a new neural network design, called warp-conditioned ray embedding (WCR), which significantly improves reconstruction. Our evaluation demonstrates performance improvements over several deep monocular reconstruction baselines on existing benchmarks.
  arXiv  Detail & Related papers  (2021-03-30T17:57:01Z)
• Secrets of 3D Implicit Object Shape Reconstruction in the Wild [92.5554695397653]
  Reconstructing high-fidelity 3D objects from sparse, partial observation is crucial for various applications in computer vision, robotics, and graphics. Recent neural implicit modeling methods show promising results on synthetic or dense datasets. But, they perform poorly on real-world data that is sparse and noisy. This paper analyzes the root cause of such deficient performance of a popular neural implicit model.
  arXiv  Detail & Related papers  (2021-01-18T03:24:48Z)
• PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding [107.02479689909164]
  In this work, we aim at facilitating research on 3D representation learning. We measure the effect of unsupervised pre-training on a large source set of 3D scenes.
  arXiv  Detail & Related papers  (2020-07-21T17:59:22Z)
• Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning [8.448611728105513]
  We propose to extend the InfoMax and contrastive learning principles on 3D shapes. We show that we can maximize the mutual information between 3D objects and their "chunks" to improve the representations in aligned datasets.
  arXiv  Detail & Related papers  (2020-06-04T00:30:26Z)

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.