Robust Image Ordinal Regression with Controllable Image Generation

• URL: http://arxiv.org/abs/2305.04213v3
• Date: Mon, 22 May 2023 02:38:52 GMT
• Title: Robust Image Ordinal Regression with Controllable Image Generation
• Authors: Yi Cheng, Haochao Ying, Renjun Hu, Jinhong Wang, Wenhao Zheng, Xiao Zhang, Danny Chen and Jian Wu
• Abstract summary: We propose a novel framework called CIG based on controllable image generation. Our main idea is to generate extra training samples with specific labels near category boundaries. We evaluate the effectiveness of our new CIG approach in three different image ordinal regression scenarios.
• Score: 12.787258917766005
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image ordinal regression has been mainly studied along the line of exploiting the order of categories. However, the issues of class imbalance and category overlap that are very common in ordinal regression were largely overlooked. As a result, the performance on minority categories is often unsatisfactory. In this paper, we propose a novel framework called CIG based on controllable image generation to directly tackle these two issues. Our main idea is to generate extra training samples with specific labels near category boundaries, and the sample generation is biased toward the less-represented categories. To achieve controllable image generation, we seek to separate structural and categorical information of images based on structural similarity, categorical similarity, and reconstruction constraints. We evaluate the effectiveness of our new CIG approach in three different image ordinal regression scenarios. The results demonstrate that CIG can be flexibly integrated with off-the-shelf image encoders or ordinal regression models to achieve improvement, and further, the improvement is more significant for minority categories.

Related papers

• GRIDS: Grouped Multiple-Degradation Restoration with Image Degradation Similarity [35.11349385659554]
  Grouped Restoration with Image Degradation Similarity (GRIDS) is a novel approach that harmonizes the competing objectives inherent in multiple-degradation restoration. Based on the degradation similarity, GRIDS divides restoration tasks into one of the optimal groups, where tasks within the same group are highly correlated. Trained models within each group show significant improvements, with an average improvement of 0.09dB over single-task upper bound models.
  arXiv  Detail & Related papers  (2024-07-17T02:43:32Z)
• Learning to Rank Patches for Unbiased Image Redundancy Reduction [80.93989115541966]
  Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. We propose a self-supervised framework for image redundancy reduction called Learning to Rank Patches.
  arXiv  Detail & Related papers  (2024-03-31T13:12:41Z)
• PSCR: Patches Sampling-based Contrastive Regression for AIGC Image Quality Assessment [1.1744028458220428]
  We propose a contrastive regression framework to leverage differences among various generated images for learning a better representation space. We conduct extensive experiments on three mainstream AIGCIQA databases including AGIQA-1K, AGIQA-3K and AIGCIQA2023. Results show significant improvements in model performance with the introduction of our proposed PSCR framework.
  arXiv  Detail & Related papers  (2023-12-10T14:18:53Z)
• Balanced Classification: A Unified Framework for Long-Tailed Object Detection [74.94216414011326]
  Conventional detectors suffer from performance degradation when dealing with long-tailed data due to a classification bias towards the majority head categories. We introduce a unified framework called BAlanced CLassification (BACL), which enables adaptive rectification of inequalities caused by disparities in category distribution. BACL consistently achieves performance improvements across various datasets with different backbones and architectures.
  arXiv  Detail & Related papers  (2023-08-04T09:11:07Z)
• Incremental Generalized Category Discovery [26.028970894707204]
  We explore the problem of Incremental Generalized Category Discovery (IGCD) This is a challenging category incremental learning setting where the goal is to develop models that can correctly categorize images from previously seen categories. We present a new method for IGCD which combines non-parametric categorization with efficient image sampling to mitigate catastrophic forgetting.
  arXiv  Detail & Related papers  (2023-04-27T16:27:11Z)
• Stable Attribute Group Editing for Reliable Few-shot Image Generation [88.59350889410794]
  We present an editing-based'' framework Attribute Group Editing (AGE) for reliable few-shot image generation. We find that class inconsistency is a common problem in GAN-generated images for downstream classification. We propose to boost the downstream classification performance of SAGE by enhancing the pixel and frequency components.
  arXiv  Detail & Related papers  (2023-02-01T01:51:47Z)
• Adaptive Fine-Grained Sketch-Based Image Retrieval [100.90633284767205]
  Recent focus on Fine-Grained Sketch-Based Image Retrieval has shifted towards generalising a model to new categories. In real-world applications, a trained FG-SBIR model is often applied to both new categories and different human sketchers. We introduce a novel model-agnostic meta-learning (MAML) based framework with several key modifications.
  arXiv  Detail & Related papers  (2022-07-04T21:07:20Z)
• A Few Guidelines for Incremental Few-Shot Segmentation [57.34237650765928]
  Given a pretrained segmentation model and few images containing novel classes, our goal is to learn to segment novel classes while retaining the ability to segment previously seen ones. We show how the main problems of end-to-end training in this scenario are. i) the drift of the batch-normalization statistics toward novel classes that we can fix with batch renormalization and. ii) the forgetting of old classes, that we can fix with regularization strategies.
  arXiv  Detail & Related papers  (2020-11-30T20:45:56Z)
• C3VQG: Category Consistent Cyclic Visual Question Generation [51.339348810676896]
  Visual Question Generation (VQG) is the task of generating natural questions based on an image. In this paper, we try to exploit the different visual cues and concepts in an image to generate questions using a variational autoencoder (VAE) without ground-truth answers. Our approach solves two major shortcomings of existing VQG systems: (i) minimize the level of supervision and (ii) replace generic questions with category relevant generations.
  arXiv  Detail & Related papers  (2020-05-15T20:25:03Z)

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.