Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

• URL: http://arxiv.org/abs/2405.09782v2
• Date: Mon, 27 May 2024 08:31:48 GMT
• Title: Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection
• Authors: Feiran Li, Qianqian Xu, Shilong Bao, Zhiyong Yang, Runmin Cong, Xiaochun Cao, Qingming Huang,
• Abstract summary: Current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. We develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes.
• Score: 133.66006666465447
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://github.com/Ferry-Li/SI-SOD.

Related papers

• Better Sampling, towards Better End-to-end Small Object Detection [7.7473020808686694]
  Small object detection remains unsatisfactory due to limited characteristics and high density and mutual overlap. We propose methods enhancing sampling within an end-to-end framework. Our model demonstrates a significant enhancement, achieving a 2.9% increase in average precision (AP) over the state-of-the-art (SOTA) on the VisDrone dataset.
  arXiv  Detail & Related papers  (2024-05-17T04:37:44Z)
• Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection [55.2480439325792]
  We present an in-depth evaluation of an object detection model that integrates the LSKNet backbone with the DiffusionDet head. The proposed model achieves a mean average precision (MAP) of approximately 45.7%, which is a significant improvement. This advancement underscores the effectiveness of the proposed modifications and sets a new benchmark in aerial image analysis.
  arXiv  Detail & Related papers  (2023-11-21T19:49:13Z)
• Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union [113.20223082664681]
  We propose the use of fine-grained mIoUs along with corresponding worst-case metrics. These fine-grained metrics offer less bias towards large objects, richer statistical information, and valuable insights into model and dataset auditing. Our benchmark study highlights the necessity of not basing evaluations on a single metric and confirms that fine-grained mIoUs reduce the bias towards large objects.
  arXiv  Detail & Related papers  (2023-10-30T03:45:15Z)
• ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection [24.085715205081385]
  We denote size of an object as the number of pixels it covers in an image and size imbalance as the over-representation of certain sizes of objects in a dataset. We propose a novel ARchitectUre-agnostic BAlanced Loss (ARUBA) that can be applied as a plugin on top of any object detection model.
  arXiv  Detail & Related papers  (2022-10-10T11:28:16Z)
• Scale-Equivalent Distillation for Semi-Supervised Object Detection [57.59525453301374]
  Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based on self-training, generating hard pseudo-labels by a teacher model on unlabeled data as supervisory signals. We analyze the challenges these methods meet with the empirical experiment results. We introduce a novel approach, Scale-Equivalent Distillation (SED), which is a simple yet effective end-to-end knowledge distillation framework robust to large object size variance and class imbalance.
  arXiv  Detail & Related papers  (2022-03-23T07:33:37Z)
• Multiscale IoU: A Metric for Evaluation of Salient Object Detection with Fine Structures [5.098461305284216]
  General-purpose object-detection algorithms often dismiss the fine structure of detected objects. We present a new metric that is a marriage of a popular evaluation metric, namely Intersection over Union (IoU), and a geometrical concept, called fractal dimension. We show that MIoU is indeed sensitive to the fine boundary structures which are completely overlooked by IoU and f1-score.
  arXiv  Detail & Related papers  (2021-05-30T15:31:42Z)
• Objects are Different: Flexible Monocular 3D Object Detection [87.82253067302561]
  We propose a flexible framework for monocular 3D object detection which explicitly decouples the truncated objects and adaptively combines multiple approaches for object depth estimation. Experiments demonstrate that our method outperforms the state-of-the-art method by relatively 27% for the moderate level and 30% for the hard level in the test set of KITTI benchmark.
  arXiv  Detail & Related papers  (2021-04-06T07:01:28Z)
• Shift Equivariance in Object Detection [8.03777903218606]
  Recent works have shown that CNN-based classifiers are not shift invariant. It is unclear to what extent this could impact object detection, mainly because of the architectural differences between the two and the dimensionality of the prediction space of modern detectors. We propose an evaluation metric, built upon a greedy search of the lower and upper bounds of the mean average precision on a shifted image set.
  arXiv  Detail & Related papers  (2020-08-13T10:02:02Z)
• Learning a Unified Sample Weighting Network for Object Detection [113.98404690619982]
  Region sampling or weighting is significantly important to the success of modern region-based object detectors. We argue that sample weighting should be data-dependent and task-dependent. We propose a unified sample weighting network to predict a sample's task weights.
  arXiv  Detail & Related papers  (2020-06-11T16:19:16Z)

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.