MetaFormer: A Unified Meta Framework for Fine-Grained Recognition

• URL: http://arxiv.org/abs/2203.02751v1
• Date: Sat, 5 Mar 2022 14:12:25 GMT
• Title: MetaFormer: A Unified Meta Framework for Fine-Grained Recognition
• Authors: Qishuai Diao, Yi Jiang, Bin Wen, Jia Sun, Zehuan Yuan
• Abstract summary: We propose a unified and strong meta-framework for fine-grained visual classification. In practice, MetaFormer provides a simple yet effective approach to address the joint learning of vision and various meta-information. In experiments, MetaFormer can effectively use various meta-information to improve the performance of fine-grained recognition.
• Score: 16.058297377539418
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-Grained Visual Classification(FGVC) is the task that requires recognizing the objects belonging to multiple subordinate categories of a super-category. Recent state-of-the-art methods usually design sophisticated learning pipelines to tackle this task. However, visual information alone is often not sufficient to accurately differentiate between fine-grained visual categories. Nowadays, the meta-information (e.g., spatio-temporal prior, attribute, and text description) usually appears along with the images. This inspires us to ask the question: Is it possible to use a unified and simple framework to utilize various meta-information to assist in fine-grained identification? To answer this problem, we explore a unified and strong meta-framework(MetaFormer) for fine-grained visual classification. In practice, MetaFormer provides a simple yet effective approach to address the joint learning of vision and various meta-information. Moreover, MetaFormer also provides a strong baseline for FGVC without bells and whistles. Extensive experiments demonstrate that MetaFormer can effectively use various meta-information to improve the performance of fine-grained recognition. In a fair comparison, MetaFormer can outperform the current SotA approaches with only vision information on the iNaturalist2017 and iNaturalist2018 datasets. Adding meta-information, MetaFormer can exceed the current SotA approaches by 5.9% and 5.3%, respectively. Moreover, MetaFormer can achieve 92.3% and 92.7% on CUB-200-2011 and NABirds, which significantly outperforms the SotA approaches. The source code and pre-trained models are released athttps://github.com/dqshuai/MetaFormer.

Related papers

• Context-Aware Meta-Learning [52.09326317432577]
  We propose a meta-learning algorithm that emulates Large Language Models by learning new visual concepts during inference without fine-tuning. Our approach exceeds or matches the state-of-the-art algorithm, P>M>F, on 8 out of 11 meta-learning benchmarks.
  arXiv  Detail & Related papers  (2023-10-17T03:35:27Z)
• MetaFormer Baselines for Vision [173.16644649968393]
  We introduce several baseline models under MetaFormer using the most basic or common mixers. We find that MetaFormer ensures solid lower bound of performance. We also find that a new activation, StarReLU, reduces FLOPs of activation compared with GELU yet achieves better performance.
  arXiv  Detail & Related papers  (2022-10-24T17:59:57Z)
• MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks [7.501059084460409]
  Heterogeneous Information Network (HIN) is essential to study complicated networks containing multiple edge types and node types. Existing meta-path generation approaches cannot fully exploit the rich textual information in HINs. We propose MetaFill, a text-infilling-based approach for meta-path generation.
  arXiv  Detail & Related papers  (2022-10-14T03:34:09Z)
• Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning [4.952681349410351]
  Few-shot object detection (FSOD) aims to classify and detect few images of novel categories. We propose a hierarchical attention network with sequentially large receptive fields to fully exploit the query and support images. Our method brings 2.3, 1.0, 1.3, 3.4 and 2.4% AP improvements for 1-30 shots object detection on COCO dataset.
  arXiv  Detail & Related papers  (2022-08-15T07:29:31Z)
• Does MAML Only Work via Feature Re-use? A Data Centric Perspective [19.556093984142418]
  We provide empirical results that shed some light on how meta-learned MAML representations function. We show that it is possible to define a family of synthetic benchmarks that result in a low degree of feature re-use. We conjecture the core challenge of re-thinking meta-learning is in the design of few-shot learning data sets and benchmarks.
  arXiv  Detail & Related papers  (2021-12-24T20:18:38Z)
• Learning Meta-class Memory for Few-Shot Semantic Segmentation [90.28474742651422]
  We introduce the concept of meta-class, which is the meta information shareable among all classes. We propose a novel Meta-class Memory based few-shot segmentation method (MM-Net), where we introduce a set of learnable memory embeddings. Our proposed MM-Net achieves 37.5% mIoU on the COCO dataset in 1-shot setting, which is 5.1% higher than the previous state-of-the-art.
  arXiv  Detail & Related papers  (2021-08-06T06:29:59Z)
• MetaDelta: A Meta-Learning System for Few-shot Image Classification [71.06324527247423]
  We propose MetaDelta, a novel practical meta-learning system for the few-shot image classification. Each meta-learner in MetaDelta is composed of a unique pretrained encoder fine-tuned by batch training and parameter-free decoder used for prediction.
  arXiv  Detail & Related papers  (2021-02-22T02:57:22Z)
• Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning [79.25478727351604]
  We explore a simple process: meta-learning over a whole-classification pre-trained model on its evaluation metric. We observe this simple method achieves competitive performance to state-of-the-art methods on standard benchmarks.
  arXiv  Detail & Related papers  (2020-03-09T20:06:36Z)
• Incremental Meta-Learning via Indirect Discriminant Alignment [118.61152684795178]
  We develop a notion of incremental learning during the meta-training phase of meta-learning. Our approach performs favorably at test time as compared to training a model with the full meta-training set.
  arXiv  Detail & Related papers  (2020-02-11T01:39:12Z)

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.