Learning of Visual Relations: The Devil is in the Tails

• URL: http://arxiv.org/abs/2108.09668v1
• Date: Sun, 22 Aug 2021 08:59:35 GMT
• Title: Learning of Visual Relations: The Devil is in the Tails
• Authors: Alakh Desai, Tz-Ying Wu, Subarna Tripathi, Nuno Vasconcelos
• Abstract summary: Visual relation learning is a long-tailed problem, due to the nature of joint reasoning about groups of objects. In this paper, we explore an alternative hypothesis, denoted the Devil is in the Tails. Under this hypothesis, better performance is achieved by keeping the model simple but improving its ability to cope with long-tailed distributions.
• Score: 59.737494875502215
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Significant effort has been recently devoted to modeling visual relations. This has mostly addressed the design of architectures, typically by adding parameters and increasing model complexity. However, visual relation learning is a long-tailed problem, due to the combinatorial nature of joint reasoning about groups of objects. Increasing model complexity is, in general, ill-suited for long-tailed problems due to their tendency to overfit. In this paper, we explore an alternative hypothesis, denoted the Devil is in the Tails. Under this hypothesis, better performance is achieved by keeping the model simple but improving its ability to cope with long-tailed distributions. To test this hypothesis, we devise a new approach for training visual relationships models, which is inspired by state-of-the-art long-tailed recognition literature. This is based on an iterative decoupled training scheme, denoted Decoupled Training for Devil in the Tails (DT2). DT2 employs a novel sampling approach, Alternating Class-Balanced Sampling (ACBS), to capture the interplay between the long-tailed entity and predicate distributions of visual relations. Results show that, with an extremely simple architecture, DT2-ACBS significantly outperforms much more complex state-of-the-art methods on scene graph generation tasks. This suggests that the development of sophisticated models must be considered in tandem with the long-tailed nature of the problem.

Related papers

• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• RelVAE: Generative Pretraining for few-shot Visual Relationship Detection [2.2230760534775915]
  We present the first pretraining method for few-shot predicate classification that does not require any annotated relations. We construct few-shot training splits and show quantitative experiments on VG200 and VRD datasets.
  arXiv  Detail & Related papers  (2023-11-27T19:08:08Z)
• Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learning [52.021899899683675]
  In scenarios with long-tailed distributions, the model's ability to identify tail classes is limited due to the under-representation of tail samples. We propose an Orthogonal Uncertainty Representation (OUR) of feature embedding and an end-to-end training strategy to improve the long-tail phenomenon of model robustness.
  arXiv  Detail & Related papers  (2023-10-16T05:50:34Z)
• Alleviating the Effect of Data Imbalance on Adversarial Training [26.36714114672729]
  We study adversarial training on datasets that obey the long-tailed distribution. We propose a new adversarial training framework -- Re-balancing Adversarial Training (REAT)
  arXiv  Detail & Related papers  (2023-07-14T07:01:48Z)
• Improving Tail-Class Representation with Centroid Contrastive Learning [145.73991900239017]
  We propose interpolative centroid contrastive learning (ICCL) to improve long-tailed representation learning. ICCL interpolates two images from a class-agnostic sampler and a class-aware sampler, and trains the model such that the representation of the ICCL can be used to retrieve the centroids for both source classes. Our result shows a significant accuracy gain of 2.8% on the iNaturalist 2018 dataset with a real-world long-tailed distribution.
  arXiv  Detail & Related papers  (2021-10-19T15:24:48Z)
• Exploring Task Difficulty for Few-Shot Relation Extraction [22.585574542329677]
  Few-shot relation extraction (FSRE) focuses on recognizing novel relations by learning with merely a handful of annotated instances. We introduce a novel approach based on contrastive learning that learns better representations by exploiting relation label information.
  arXiv  Detail & Related papers  (2021-09-12T09:40:33Z)
• A Multi-Level Attention Model for Evidence-Based Fact Checking [58.95413968110558]
  We present a simple model that can be trained on sequence structures. Results on a large-scale dataset for Fact Extraction and VERification show that our model outperforms the graph-based approaches.
  arXiv  Detail & Related papers  (2021-06-02T05:40:12Z)
• RH-Net: Improving Neural Relation Extraction via Reinforcement Learning and Hierarchical Relational Searching [2.1828601975620257]
  We propose a novel framework named RH-Net, which utilizes Reinforcement learning and Hierarchical relational searching module to improve relation extraction. We then propose the hierarchical relational searching module to share the semantics from correlative instances between data-rich and data-poor classes.
  arXiv  Detail & Related papers  (2020-10-27T12:50:27Z)
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
  We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
  arXiv  Detail & Related papers  (2020-02-21T05:00:01Z)

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.