Long-tail Detection with Effective Class-Margins

• URL: http://arxiv.org/abs/2301.09724v1
• Date: Mon, 23 Jan 2023 21:25:24 GMT
• Title: Long-tail Detection with Effective Class-Margins
• Authors: Jang Hyun Cho, Philipp Kr\"ahenb\"uhl
• Abstract summary: We show how the commonly used mean average precision evaluation metric on an unknown test set is bound by a margin-based binary classification error. We optimize margin-based binary classification error with a novel surrogate objective called text-Effective Class-Margin Loss (ECM)
• Score: 4.18804572788063
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large-scale object detection and instance segmentation face a severe data imbalance. The finer-grained object classes become, the less frequent they appear in our datasets. However, at test-time, we expect a detector that performs well for all classes and not just the most frequent ones. In this paper, we provide a theoretical understanding of the long-trail detection problem. We show how the commonly used mean average precision evaluation metric on an unknown test set is bound by a margin-based binary classification error on a long-tailed object detection training set. We optimize margin-based binary classification error with a novel surrogate objective called \textbf{Effective Class-Margin Loss} (ECM). The ECM loss is simple, theoretically well-motivated, and outperforms other heuristic counterparts on LVIS v1 benchmark over a wide range of architecture and detectors. Code is available at \url{https://github.com/janghyuncho/ECM-Loss}.

Related papers

• A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection [52.228708947607636]
  This paper introduces a comprehensive visual anomaly detection benchmark, ADer, which is a modular framework for new methods. The benchmark includes multiple datasets from industrial and medical domains, implementing fifteen state-of-the-art methods and nine comprehensive metrics. We objectively reveal the strengths and weaknesses of different methods and provide insights into the challenges and future directions of multi-class visual anomaly detection.
  arXiv  Detail & Related papers  (2024-06-05T13:40:07Z)
• 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)
• Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker [57.49330031751386]
  We find achievable information-theoretic lower bounds on loss in the presence of a test-time attacker for multi-class classifiers on any discrete dataset. We provide a general framework for finding the optimal 0-1 loss that revolves around the construction of a conflict hypergraph from the data and adversarial constraints.
  arXiv  Detail & Related papers  (2023-02-21T15:17:13Z)
• Long-tailed Instance Segmentation using Gumbel Optimized Loss [29.240427080642]
  We develop a Gumbel Optimized Loss (GOL) method for long-tailed detection and segmentation. GOL significantly outperforms the best state-of-the-art method by 1.1% on AP.
  arXiv  Detail & Related papers  (2022-07-22T08:20:23Z)
• Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation [17.149364927872014]
  We present a novel loss function, called class-agnostic segmentation (CAS) loss. We show that the CAS loss function is sparse, bounded, and robust to class-imbalance.
  arXiv  Detail & Related papers  (2021-07-16T12:26:31Z)
• Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation [17.532822703595766]
  We present a novel loss function, called class-agnostic segmentation (CAS) loss. We show that the CAS loss function is sparse, bounded, and robust to class-imbalance. We investigate the performance against the state-of-the-art methods in two settings of low and high-fidelity training data.
  arXiv  Detail & Related papers  (2020-10-28T07:11:15Z)
• The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation [93.17367076148348]
  We investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset. We unveil that a major cause is the inaccurate classification of object proposals. We propose a simple calibration framework to more effectively alleviate classification head bias with a bi-level class balanced sampling approach.
  arXiv  Detail & Related papers  (2020-07-23T12:49:07Z)
• Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax [88.11979569564427]
  We provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution. We propose a novel balanced group softmax (BAGS) module for balancing the classifiers within the detection frameworks through group-wise training. Extensive experiments on the very recent long-tail large vocabulary object recognition benchmark LVIS show that our proposed BAGS significantly improves the performance of detectors.
  arXiv  Detail & Related papers  (2020-06-18T10:24:26Z)
• Frustratingly Simple Few-Shot Object Detection [98.42824677627581]
  We find that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task. Such a simple approach outperforms the meta-learning methods by roughly 220 points on current benchmarks.
  arXiv  Detail & Related papers  (2020-03-16T00:29:14Z)

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.