Multi-Task Incremental Learning for Object Detection
- URL: http://arxiv.org/abs/2002.05347v3
- Date: Wed, 18 Nov 2020 20:31:18 GMT
- Title: Multi-Task Incremental Learning for Object Detection
- Authors: Xialei Liu, Hao Yang, Avinash Ravichandran, Rahul Bhotika, Stefano
Soatto
- Abstract summary: Multi-task learns multiple tasks, while sharing knowledge and computation among them.
It suffers from catastrophic forgetting of previous knowledge when learned incrementally without access to the old data.
- Score: 71.57155077119839
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Multi-task learns multiple tasks, while sharing knowledge and computation
among them. However, it suffers from catastrophic forgetting of previous
knowledge when learned incrementally without access to the old data. Most
existing object detectors are domain-specific and static, while some are
learned incrementally but only within a single domain. Training an object
detector incrementally across various domains has rarely been explored. In this
work, we propose three incremental learning scenarios across various domains
and categories for object detection. To mitigate catastrophic forgetting,
attentive feature distillation is proposed to leverages both bottom-up and
top-down attentions to extract important information for distillation. We then
systematically analyze the proposed distillation method in different scenarios.
We find out that, contrary to common understanding, domain gaps have smaller
negative impact on incremental detection, while category differences are
problematic. For the difficult cases, where the domain gaps and especially
category differences are large, we explore three different exemplar sampling
methods and show the proposed adaptive sampling method is effective to select
diverse and informative samples from entire datasets, to further prevent
forgetting. Experimental results show that we achieve the significant
improvement in three different scenarios across seven object detection
benchmark datasets.
Related papers
- Regularized Contrastive Partial Multi-view Outlier Detection [76.77036536484114]
We propose a novel method named Regularized Contrastive Partial Multi-view Outlier Detection (RCPMOD)
In this framework, we utilize contrastive learning to learn view-consistent information and distinguish outliers by the degree of consistency.
Experimental results on four benchmark datasets demonstrate that our proposed approach could outperform state-of-the-art competitors.
arXiv Detail & Related papers (2024-08-02T14:34:27Z) - Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment [17.485775402656127]
A base detector can outperform existing methods for single domain generalization by a good margin.
We introduce a method to align detections from multiple views, considering both classification and localization outputs.
Our approach is detector-agnostic and can be seamlessly applied to both single-stage and two-stage detectors.
arXiv Detail & Related papers (2024-05-23T12:29:25Z) - Multimodal 3D Object Detection on Unseen Domains [37.142470149311904]
Domain adaptation approaches assume access to unannotated samples from the test distribution to address this problem.
We propose CLIX$text3D$, a multimodal fusion and supervised contrastive learning framework for 3D object detection.
We show that CLIX$text3D$ yields state-of-the-art domain generalization performance under multiple dataset shifts.
arXiv Detail & Related papers (2024-04-17T21:47:45Z) - Few-Shot Object Detection with Sparse Context Transformers [37.106378859592965]
Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data.
We propose a novel sparse context transformer (SCT) that effectively leverages object knowledge in the source domain, and automatically learns a sparse context from only few training images in the target domain.
We evaluate the proposed method on two challenging few-shot object detection benchmarks, and empirical results show that the proposed method obtains competitive performance compared to the related state-of-the-art.
arXiv Detail & Related papers (2024-02-14T17:10:01Z) - DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detection [2.207918236777924]
We propose a novel 3D domain adaptive class-incremental object detection framework, DA-CIL.
We design a novel dual-domain copy-paste augmentation method to construct multiple augmented domains for diversifying training distributions.
Experiments on various datasets demonstrate the effectiveness of the proposed method over baselines.
arXiv Detail & Related papers (2022-12-05T06:45:27Z) - Detection Hub: Unifying Object Detection Datasets via Query Adaptation
on Language Embedding [137.3719377780593]
A new design (named Detection Hub) is dataset-aware and category-aligned.
It mitigates the dataset inconsistency and provides coherent guidance for the detector to learn across multiple datasets.
The categories across datasets are semantically aligned into a unified space by replacing one-hot category representations with word embedding.
arXiv Detail & Related papers (2022-06-07T17:59:44Z) - Multi-Label Few-Shot Learning for Aspect Category Detection [23.92900196246631]
Aspect category detection (ACD) in sentiment analysis aims to identify the aspect categories mentioned in a sentence.
Existing few-shot learning approaches mainly focus on single-label predictions.
We propose a multi-label few-shot learning method based on the prototypical network.
arXiv Detail & Related papers (2021-05-29T01:56:11Z) - Anomaly Detection in Video via Self-Supervised and Multi-Task Learning [113.81927544121625]
Anomaly detection in video is a challenging computer vision problem.
In this paper, we approach anomalous event detection in video through self-supervised and multi-task learning at the object level.
arXiv Detail & Related papers (2020-11-15T10:21:28Z) - Few-shot Learning for Multi-label Intent Detection [59.66787898744991]
State-of-the-art work estimates label-instance relevance scores and uses a threshold to select multiple associated intent labels.
Experiments on two datasets show that the proposed model significantly outperforms strong baselines in both one-shot and five-shot settings.
arXiv Detail & Related papers (2020-10-11T14:42:18Z) - Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation [62.29076080124199]
This paper proposes a novel coarse-to-fine feature adaptation approach to cross-domain object detection.
At the coarse-grained stage, foreground regions are extracted by adopting the attention mechanism, and aligned according to their marginal distributions.
At the fine-grained stage, we conduct conditional distribution alignment of foregrounds by minimizing the distance of global prototypes with the same category but from different domains.
arXiv Detail & Related papers (2020-03-23T13:40:06Z)
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.