Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detection

• URL: http://arxiv.org/abs/2111.06639v1
• Date: Fri, 12 Nov 2021 10:11:56 GMT
• Title: Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detection
• Authors: Ashutosh Agarwal and Anay Majee and Anbumani Subramanian and Chetan Arora
• Abstract summary: Few-shot object detection (FSOD) localizes and classifies objects in an image given only a few data samples. Recent trends in FSOD research show the adoption of metric and meta-learning techniques, which are prone to catastrophic forgetting and class confusion. We introduce Attention Guided Cosine Margin (AGCM) that facilitates the creation of tighter and well separated class-specific feature clusters.
• Score: 5.821060995749903
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Few-shot object detection (FSOD) localizes and classifies objects in an image given only a few data samples. Recent trends in FSOD research show the adoption of metric and meta-learning techniques, which are prone to catastrophic forgetting and class confusion. To overcome these pitfalls in metric learning based FSOD techniques, we introduce Attention Guided Cosine Margin (AGCM) that facilitates the creation of tighter and well separated class-specific feature clusters in the classification head of the object detector. Our novel Attentive Proposal Fusion (APF) module minimizes catastrophic forgetting by reducing the intra-class variance among co-occurring classes. At the same time, the proposed Cosine Margin Cross-Entropy loss increases the angular margin between confusing classes to overcome the challenge of class confusion between already learned (base) and newly added (novel) classes. We conduct our experiments on the challenging India Driving Dataset (IDD), which presents a real-world class-imbalanced setting alongside popular FSOD benchmark PASCAL-VOC. Our method outperforms State-of-the-Art (SoTA) approaches by up to 6.4 mAP points on the IDD-OS and up to 2.0 mAP points on the IDD-10 splits for the 10-shot setting. On the PASCAL-VOC dataset, we outperform existing SoTA approaches by up to 4.9 mAP points.

Related papers

• SMILe: Leveraging Submodular Mutual Information For Robust Few-Shot Object Detection [2.0755366440393743]
  Confusion and forgetting of object classes have been challenges of prime interest in Few-Shot Object Detection (FSOD) We introduce a novel Submodular Mutual Information Learning framework which adopts mutual information functions. Our proposed approach generalizes to several existing approaches in FSOD, agnostic of the backbone architecture.
  arXiv  Detail & Related papers  (2024-07-02T20:53:43Z)
• Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning [42.14439854721613]
  We propose a prototypical network with a Bayesian learning-driven contrastive loss (BLCL) tailored specifically for class-incremental learning scenarios. Our approach dynamically adapts the balance between the cross-entropy and contrastive loss functions with a Bayesian learning technique.
  arXiv  Detail & Related papers  (2024-05-17T19:49:02Z)
• Controllable Relation Disentanglement for Few-Shot Class-Incremental Learning [82.79371269942146]
  We propose to tackle FewShot Class-Incremental Learning (FSCIL) from a new perspective, i.e., relation disentanglement. The challenge of disentangling spurious correlations lies in the poor controllability of FSCIL. We propose a new simple-yeteffective method, called ConTrollable Relation-disentang FewShot Class-Incremental Learning (CTRL-FSCIL)
  arXiv  Detail & Related papers  (2024-03-17T03:16:59Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• Few-shot Object Detection with Refined Contrastive Learning [4.520231308678286]
  We propose a novel few-shot object detection (FSOD) method with Refined Contrastive Learning (FSRC) A pre-determination component is introduced to find out the Resemblance Group from novel classes which contains confusable classes. RCL is pointedly performed on this group of classes in order to increase the inter-class distances among them.
  arXiv  Detail & Related papers  (2022-11-24T09:34:20Z)
• Zero-Shot Temporal Action Detection via Vision-Language Prompting [134.26292288193298]
  We propose a novel zero-Shot Temporal Action detection model via Vision-LanguagE prompting (STALE) Our model significantly outperforms state-of-the-art alternatives. Our model also yields superior results on supervised TAD over recent strong competitors.
  arXiv  Detail & Related papers  (2022-07-17T13:59:46Z)
• Continual Learning For On-Device Environmental Sound Classification [63.81276321857279]
  We propose a simple and efficient continual learning method for on-device environmental sound classification. Our method selects the historical data for the training by measuring the per-sample classification uncertainty.
  arXiv  Detail & Related papers  (2022-07-15T12:13:04Z)
• Spacing Loss for Discovering Novel Categories [72.52222295216062]
  Novel Class Discovery (NCD) is a learning paradigm, where a machine learning model is tasked to semantically group instances from unlabeled data. We first characterize existing NCD approaches into single-stage and two-stage methods based on whether they require access to labeled and unlabeled data together. We devise a simple yet powerful loss function that enforces separability in the latent space using cues from multi-dimensional scaling.
  arXiv  Detail & Related papers  (2022-04-22T09:37:11Z)
• 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)
• Meta Guided Metric Learner for Overcoming Class Confusion in Few-Shot Road Object Detection [0.3867363075280544]
  Few-Shot Object Detection techniques extend the knowledge from existing base object classes to learn novel road objects. We introduce a novel Meta Guided Metric (MGML) to overcome class confusion in FSOD. Our method outperforms State-of-the-Art (SoTA) approaches in FSOD on the India Driving Learner dataset.
  arXiv  Detail & Related papers  (2021-10-28T12:51:08Z)

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.