Preview-based Category Contrastive Learning for Knowledge Distillation

• URL: http://arxiv.org/abs/2410.14143v1
• Date: Fri, 18 Oct 2024 03:31:00 GMT
• Title: Preview-based Category Contrastive Learning for Knowledge Distillation
• Authors: Muhe Ding, Jianlong Wu, Xue Dong, Xiaojie Li, Pengda Qin, Tian Gan, Liqiang Nie,
• Abstract summary: 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.
• Score: 53.551002781828146
• License:
• Abstract: Knowledge distillation is a mainstream algorithm in model compression by transferring knowledge from the larger model (teacher) to the smaller model (student) to improve the performance of student. Despite many efforts, existing methods mainly investigate the consistency between instance-level feature representation or prediction, which neglects the category-level information and the difficulty of each sample, leading to undesirable performance. To address these issues, 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 in a contrastive learning fashion, which can explicitly optimize the category representation and explore the distinct correlation between representations of instances and categories, contributing to discriminative category centers and better classification results. Besides, we introduce a novel preview strategy to dynamically determine how much the student should learn from each sample according to their difficulty. Different from existing methods that treat all samples equally and curriculum learning that simply filters out hard samples, our method assigns a small weight for hard instances as a preview to better guide the student training. Extensive experiments on several challenging datasets, including CIFAR-100 and ImageNet, demonstrate the superiority over state-of-the-art methods.

Related papers

• A Study on Representation Transfer for Few-Shot Learning [5.717951523323085]
  Few-shot classification aims to learn to classify new object categories well using only a few labeled examples. In this work we perform a systematic study of various feature representations for few-shot classification. We find that learning from more complex tasks tend to give better representations for few-shot classification.
  arXiv  Detail & Related papers  (2022-09-05T17:56:02Z)
• Contrastive Learning for Fair Representations [50.95604482330149]
  Trained classification models can unintentionally lead to biased representations and predictions. Existing debiasing methods for classification models, such as adversarial training, are often expensive to train and difficult to optimise. We propose a method for mitigating bias by incorporating contrastive learning, in which instances sharing the same class label are encouraged to have similar representations.
  arXiv  Detail & Related papers  (2021-09-22T10:47:51Z)
• Partner-Assisted Learning for Few-Shot Image Classification [54.66864961784989]
  Few-shot Learning has been studied to mimic human visual capabilities and learn effective models without the need of exhaustive human annotation. In this paper, we focus on the design of training strategy to obtain an elemental representation such that the prototype of each novel class can be estimated from a few labeled samples. We propose a two-stage training scheme, which first trains a partner encoder to model pair-wise similarities and extract features serving as soft-anchors, and then trains a main encoder by aligning its outputs with soft-anchors while attempting to maximize classification performance.
  arXiv  Detail & Related papers  (2021-09-15T22:46:19Z)
• ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning [53.09923823663554]
  Class-level knowledge can be easily learned by humans from just a handful of samples. We propose an Explicit Class Knowledge Propagation Network (ECKPN) to address this problem. We conduct extensive experiments on four few-shot classification benchmarks, and the experimental results show that the proposed ECKPN significantly outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-06-16T02:29:43Z)
• Semi-supervised Active Learning for Instance Segmentation via Scoring Predictions [25.408505612498423]
  We propose a novel and principled semi-supervised active learning framework for instance segmentation. Specifically, we present an uncertainty sampling strategy named Triplet Scoring Predictions (TSP) to explicitly incorporate samples ranking clues from classes, bounding boxes and masks. Results on medical images datasets demonstrate that the proposed method results in the embodiment of knowledge from available data in a meaningful way.
  arXiv  Detail & Related papers  (2020-12-09T02:36:52Z)
• Few-shot Classification via Adaptive Attention [93.06105498633492]
  We propose a novel few-shot learning method via optimizing and fast adapting the query sample representation based on very few reference samples. As demonstrated experimentally, the proposed model achieves state-of-the-art classification results on various benchmark few-shot classification and fine-grained recognition datasets.
  arXiv  Detail & Related papers  (2020-08-06T05:52:59Z)
• UniT: Unified Knowledge Transfer for Any-shot Object Detection and Segmentation [52.487469544343305]
  Methods for object detection and segmentation rely on large scale instance-level annotations for training. We propose an intuitive and unified semi-supervised model that is applicable to a range of supervision.
  arXiv  Detail & Related papers  (2020-06-12T22:45:47Z)
• Dynamic Sampling for Deep Metric Learning [7.010669841466896]
  Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. A dynamic sampling strategy is proposed to organize the training pairs in an easy-to-hard order to feed into the network. It allows the network to learn general boundaries between categories from the easy training pairs at its early stages and finalize the details of the model mainly relying on the hard training samples in the later.
  arXiv  Detail & Related papers  (2020-04-24T09:47:23Z)

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.