Train a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning

• URL: http://arxiv.org/abs/2102.04848v1
• Date: Tue, 9 Feb 2021 14:44:18 GMT
• Title: Train a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning
• Authors: Yu Liu, Lianghua Huang, Pan Pan, Bin Wang, Yinghui Xu, Rong Jin
• Abstract summary: This paper presents a simple unsupervised visual representation learning method with a pretext task of discriminating all images in a dataset using a parametric, instance-level computation. The overall framework is a replica of a supervised classification model, where semantic classes (e.g., dog, bird, and ship) are replaced by instance IDs. scaling up the classification task from thousands of semantic labels to millions of instance labels brings specific challenges including 1) the large-scale softmax classifier; 2) the slow convergence due to the infrequent visiting of instance samples; and 3) the massive number of negative classes that can be noisy.
• Score: 45.510042484456854
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper presents a simple unsupervised visual representation learning method with a pretext task of discriminating all images in a dataset using a parametric, instance-level classifier. The overall framework is a replica of a supervised classification model, where semantic classes (e.g., dog, bird, and ship) are replaced by instance IDs. However, scaling up the classification task from thousands of semantic labels to millions of instance labels brings specific challenges including 1) the large-scale softmax computation; 2) the slow convergence due to the infrequent visiting of instance samples; and 3) the massive number of negative classes that can be noisy. This work presents several novel techniques to handle these difficulties. First, we introduce a hybrid parallel training framework to make large-scale training feasible. Second, we present a raw-feature initialization mechanism for classification weights, which we assume offers a contrastive prior for instance discrimination and can clearly speed up converge in our experiments. Finally, we propose to smooth the labels of a few hardest classes to avoid optimizing over very similar negative pairs. While being conceptually simple, our framework achieves competitive or superior performance compared to state-of-the-art unsupervised approaches, i.e., SimCLR, MoCoV2, and PIC under ImageNet linear evaluation protocol and on several downstream visual tasks, verifying that full instance classification is a strong pretraining technique for many semantic visual tasks.

Related papers

• Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Good Instance Classifier is All You Need [18.832471712088353]
  We propose an instance-level weakly supervised contrastive learning algorithm for the first time under the MIL setting. We also propose an accurate pseudo label generation method through prototype learning.
  arXiv  Detail & Related papers  (2023-07-05T12:44:52Z)
• Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition [94.04041301504567]
  Few-shot visual recognition refers to recognize novel visual concepts from a few labeled instances. We propose a novel metric-based meta-learning framework termed instance-adaptive class representation learning network (ICRL-Net) for few-shot visual recognition.
  arXiv  Detail & Related papers  (2022-09-07T10:00:18Z)
• Weakly Supervised Contrastive Learning [68.47096022526927]
  We introduce a weakly supervised contrastive learning framework (WCL) to tackle this issue. WCL achieves 65% and 72% ImageNet Top-1 Accuracy using ResNet50, which is even higher than SimCLRv2 with ResNet101.
  arXiv  Detail & Related papers  (2021-10-10T12:03:52Z)
• Self-Supervised Classification Network [3.8073142980733]
  Self-supervised end-to-end classification neural network learns labels and representations simultaneously. First unsupervised end-to-end classification network to perform well on the large-scale ImageNet dataset.
  arXiv  Detail & Related papers  (2021-03-19T19:29:42Z)
• Learning and Evaluating Representations for Deep One-class Classification [59.095144932794646]
  We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks.
  arXiv  Detail & Related papers  (2020-11-04T23:33:41Z)
• Towards Cross-Granularity Few-Shot Learning: Coarse-to-Fine Pseudo-Labeling with Visual-Semantic Meta-Embedding [13.063136901934865]
  Few-shot learning aims at rapidly adapting to novel categories with only a handful of samples at test time. In this paper, we advance the few-shot classification paradigm towards a more challenging scenario, i.e., cross-granularity few-shot classification. We approximate the fine-grained data distribution by greedy clustering of each coarse-class into pseudo-fine-classes according to the similarity of image embeddings.
  arXiv  Detail & Related papers  (2020-07-11T03:44:21Z)
• 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)
• Unsupervised Person Re-identification via Softened Similarity Learning [122.70472387837542]
  Person re-identification (re-ID) is an important topic in computer vision. This paper studies the unsupervised setting of re-ID, which does not require any labeled information. Experiments on two image-based and video-based datasets demonstrate state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-04-07T17:16:41Z)

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.