Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning

• URL: http://arxiv.org/abs/2104.01832v1
• Date: Mon, 5 Apr 2021 10:05:48 GMT
• Title: Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning
• Authors: Chaoqun Wang, Xuejin Chen, Shaobo Min, Xiaoyan Sun, Houqiang Li
• Abstract summary: Generalized Zero-Shot Learning (GZSL) targets recognizing new categories by learning transferable image representations. We propose a novel Dual-Contrastive Embedding Network (DCEN) that simultaneously learns task-specific and task-independent knowledge.
• Score: 77.0715029826957
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generalized Zero-Shot Learning (GZSL) targets recognizing new categories by learning transferable image representations. Existing methods find that, by aligning image representations with corresponding semantic labels, the semantic-aligned representations can be transferred to unseen categories. However, supervised by only seen category labels, the learned semantic knowledge is highly task-specific, which makes image representations biased towards seen categories. In this paper, we propose a novel Dual-Contrastive Embedding Network (DCEN) that simultaneously learns task-specific and task-independent knowledge via semantic alignment and instance discrimination. First, DCEN leverages task labels to cluster representations of the same semantic category by cross-modal contrastive learning and exploring semantic-visual complementarity. Besides task-specific knowledge, DCEN then introduces task-independent knowledge by attracting representations of different views of the same image and repelling representations of different images. Compared to high-level seen category supervision, this instance discrimination supervision encourages DCEN to capture low-level visual knowledge, which is less biased toward seen categories and alleviates the representation bias. Consequently, the task-specific and task-independent knowledge jointly make for transferable representations of DCEN, which obtains averaged 4.1% improvement on four public benchmarks.

Related papers

• Seeing the Intangible: Survey of Image Classification into High-Level and Abstract Categories [0.20718016474717196]
  The field of Computer Vision (CV) is increasingly shifting towards high-level'' visual sensemaking tasks. This paper systematically reviews research on high-level visual understanding, focusing on Abstract Concepts (ACs) in automatic image classification.
  arXiv  Detail & Related papers  (2023-08-21T08:37:04Z)
• Semantic Representation and Dependency Learning for Multi-Label Image Recognition [76.52120002993728]
  We propose a novel and effective semantic representation and dependency learning (SRDL) framework to learn category-specific semantic representation for each category. Specifically, we design a category-specific attentional regions (CAR) module to generate channel/spatial-wise attention matrices to guide model. We also design an object erasing (OE) module to implicitly learn semantic dependency among categories by erasing semantic-aware regions.
  arXiv  Detail & Related papers  (2022-04-08T00:55:15Z)
• Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation [16.357091285395285]
  We tackle the problem of grouping unlabelled images from new classes into different semantic partitions. This is a more realistic and challenging setting than conventional semi-supervised learning. We propose a two-branch learning framework for this problem, with one branch focusing on local part-level information and the other branch focusing on overall characteristics.
  arXiv  Detail & Related papers  (2021-07-07T17:14:40Z)
• Semantic Diversity Learning for Zero-Shot Multi-label Classification [14.480713752871523]
  This study introduces an end-to-end model training for multi-label zero-shot learning. We propose to use an embedding matrix having principal embedding vectors trained using a tailored loss function. In addition, during training, we suggest up-weighting in the loss function image samples presenting higher semantic diversity to encourage the diversity of the embedding matrix.
  arXiv  Detail & Related papers  (2021-05-12T19:39:07Z)
• Revisiting Contrastive Learning for Few-Shot Classification [74.78397993160583]
  Instance discrimination based contrastive learning has emerged as a leading approach for self-supervised learning of visual representations. We show how one can incorporate supervision in the instance discrimination based contrastive self-supervised learning framework to learn representations that generalize better to novel tasks. We propose a novel model selection algorithm that can be used in conjunction with a universal embedding trained using CIDS to outperform state-of-the-art algorithms on the challenging Meta-Dataset benchmark.
  arXiv  Detail & Related papers  (2021-01-26T19:58:08Z)
• Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition [75.44233392355711]
  KGGR framework exploits prior knowledge of statistical label correlations with deep neural networks. It first builds a structured knowledge graph to correlate different labels based on statistical label co-occurrence. Then, it introduces the label semantics to guide learning semantic-specific features. It exploits a graph propagation network to explore graph node interactions.
  arXiv  Detail & Related papers  (2020-09-20T15:05:29Z)
• Zero-Shot Recognition through Image-Guided Semantic Classification [9.291055558504588]
  We present a new embedding-based framework for zero-shot learning (ZSL) Motivated by the binary relevance method for multi-label classification, we propose to inversely learn the mapping between an image and a semantic classifier. IGSC is conceptually simple and can be realized by a slight enhancement of an existing deep architecture for classification.
  arXiv  Detail & Related papers  (2020-07-23T06:22:40Z)
• Learning unbiased zero-shot semantic segmentation networks via transductive transfer [14.55508599873219]
  We propose an easy-to-implement transductive approach to alleviate the prediction bias in zero-shot semantic segmentation. Our method assumes both the source images with full pixel-level labels and unlabeled target images are available during training.
  arXiv  Detail & Related papers  (2020-07-01T14:25:13Z)
• Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning [144.94728981314717]
  We propose a novel Attribute-Induced Bias Eliminating (AIBE) module for Transductive ZSL. For the visual bias between two domains, the Mean-Teacher module is first leveraged to bridge the visual representation discrepancy between two domains. An attentional graph attribute embedding is proposed to reduce the semantic bias between seen and unseen categories. Finally, for the semantic-visual bias in the unseen domain, an unseen semantic alignment constraint is designed to align visual and semantic space in an unsupervised manner.
  arXiv  Detail & Related papers  (2020-05-31T02:08:01Z)
• Hierarchical Image Classification using Entailment Cone Embeddings [68.82490011036263]
  We first inject label-hierarchy knowledge into an arbitrary CNN-based classifier. We empirically show that availability of such external semantic information in conjunction with the visual semantics from images boosts overall performance.
  arXiv  Detail & Related papers  (2020-04-02T10:22:02Z)

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.