Weak-shot Fine-grained Classification via Similarity Transfer

• URL: http://arxiv.org/abs/2009.09197v2
• Date: Sat, 23 Oct 2021 02:57:36 GMT
• Title: Weak-shot Fine-grained Classification via Similarity Transfer
• Authors: Junjie Chen, Li Niu, Liu Liu, Liqing Zhang
• Abstract summary: We consider the problem of learning novel categories from web data with the support of a clean set of base categories. We propose a method called SimTrans to transfer pairwise semantic similarity from base categories to novel categories.
• Score: 27.123162775124204
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recognizing fine-grained categories remains a challenging task, due to the subtle distinctions among different subordinate categories, which results in the need of abundant annotated samples. To alleviate the data-hungry problem, we consider the problem of learning novel categories from web data with the support of a clean set of base categories, which is referred to as weak-shot learning. In this setting, we propose a method called SimTrans to transfer pairwise semantic similarity from base categories to novel categories. Specifically, we firstly train a similarity net on clean data, and then leverage the transferred similarity to denoise web training data using two simple yet effective strategies. In addition, we apply adversarial loss on similarity net to enhance the transferability of similarity. Comprehensive experiments demonstrate the effectiveness of our weak-shot setting and our SimTrans method. Datasets and codes are available at https://github.com/bcmi/SimTrans-Weak-Shot-Classification.

Related papers

• Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection [52.490375806093745]
  The objective of few-shot object detection (FSOD) is to detect novel objects with few training samples. We introduce the side information to alleviate the negative influences derived from the feature space and sample viewpoints. Our model outperforms the previous state-of-the-art methods, significantly improving the ability of FSOD in most shots/splits.
  arXiv  Detail & Related papers  (2025-04-09T17:24:05Z)
• Preview-based Category Contrastive Learning for Knowledge Distillation [53.551002781828146]
  We propose a novel preview-based category contrastive learning method for knowledge distillation (PCKD) It first distills the structural knowledge of both instance-level feature correspondence and the relation between instance features and category centers. It can explicitly optimize the category representation and explore the distinct correlation between representations of instances and categories.
  arXiv  Detail & Related papers  (2024-10-18T03:31:00Z)
• Balanced Classification: A Unified Framework for Long-Tailed Object Detection [74.94216414011326]
  Conventional detectors suffer from performance degradation when dealing with long-tailed data due to a classification bias towards the majority head categories. We introduce a unified framework called BAlanced CLassification (BACL), which enables adaptive rectification of inequalities caused by disparities in category distribution. BACL consistently achieves performance improvements across various datasets with different backbones and architectures.
  arXiv  Detail & Related papers  (2023-08-04T09:11:07Z)
• Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches [0.6767885381740952]
  Similarity-based approaches attempt to classify instances based on similarities between text document representations and class description representations. Zero-shot text classification approaches aim to generalize knowledge gained from a training task by assigning appropriate labels of unknown classes to text documents. This paper conducts a systematic evaluation of different similarity-based and zero-shot approaches for text classification of unseen classes.
  arXiv  Detail & Related papers  (2022-11-29T15:14:47Z)
• SimMatch: Semi-supervised Learning with Similarity Matching [43.61802702362675]
  SimMatch is a new semi-supervised learning framework that considers semantic similarity and instance similarity. With 400 epochs of training, SimMatch achieves 67.2%, and 74.4% Top-1 Accuracy with 1% and 10% labeled examples on ImageNet.
  arXiv  Detail & Related papers  (2022-03-14T08:08:48Z)
• Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity [22.706462533761986]
  We consider object detection with mixed supervision, which learns novel object categories using weak annotations. We further transfer mask prior and semantic similarity to bridge the gap between novel categories and base categories. Experimental results on three benchmark datasets demonstrate the effectiveness of our method over existing methods.
  arXiv  Detail & Related papers  (2021-10-27T05:43:09Z)
• Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning [20.66927648806676]
  We propose a novel framework for semi-supervised semantic segmentation, named adaptive equalization learning (AEL) AEL balances the training of well and badly performed categories, with a confidence bank to track category-wise performance. AEL outperforms the state-of-the-art methods by a large margin on the Cityscapes and Pascal VOC benchmarks.
  arXiv  Detail & Related papers  (2021-10-11T17:59:55Z)
• Improving filling level classification with adversarial training [90.01594595780928]
  We investigate the problem of classifying - from a single image - the level of content in a cup or a drinking glass. We use adversarial training in a generic source dataset and then refine the training with a task-specific dataset. We show that transfer learning with adversarial training in the source domain consistently improves the classification accuracy on the test set.
  arXiv  Detail & Related papers  (2021-02-08T08:32:56Z)
• Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection [69.2370349274216]
  Few-shot Intent Detection is challenging due to the scarcity of available annotated utterances. Semantic components are distilled from utterances via multi-head self-attention. Our method provides a comprehensive matching measure to enhance representations of both labeled and unlabeled instances.
  arXiv  Detail & Related papers  (2020-10-06T05:16:38Z)
• Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function [106.69643619725652]
  We develop a training strategy that allows even a simple BiLSTM model, when trained with cross-entropy loss, to achieve competitive results. We report state-of-the-art results for text classification task on several benchmark datasets.
  arXiv  Detail & Related papers  (2020-09-08T21:55:22Z)
• Dataset Bias in Few-shot Image Recognition [57.25445414402398]
  We first investigate the impact of transferable capabilities learned from base categories. Second, we investigate performance differences on different datasets from dataset structures and different few-shot learning methods.
  arXiv  Detail & Related papers  (2020-08-18T14:46:23Z)
• Sharing Matters for Generalization in Deep Metric Learning [22.243744691711452]
  This work investigates how to learn characteristics that separate between classes without the need for annotations or training data. By formulating our approach as a novel triplet sampling strategy, it can be easily applied on top of recent ranking loss frameworks.
  arXiv  Detail & Related papers  (2020-04-12T10:21:15Z)

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.