MNN: Mixed Nearest-Neighbors for Self-Supervised Learning

• URL: http://arxiv.org/abs/2311.00562v2
• Date: Mon, 13 Nov 2023 14:21:49 GMT
• Title: MNN: Mixed Nearest-Neighbors for Self-Supervised Learning
• Abstract summary: Mixed Nearest-Neighbors for Self-Supervised Learning (MNN) We present a simple self-supervised learning framework called Mixed Nearest-Neighbors for Self-Supervised Learning (MNN)
• Score: 10.327408694770709
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In contrastive self-supervised learning, positive samples are typically drawn from the same image but in different augmented views, resulting in a relatively limited source of positive samples. An effective way to alleviate this problem is to incorporate the relationship between samples, which involves including the top-K nearest neighbors of positive samples. However, the problem of false neighbors (i.e., neighbors that do not belong to the same category as the positive sample) is an objective but often overlooked challenge due to the query of neighbor samples without supervision information. In this paper, we present a simple self-supervised learning framework called Mixed Nearest-Neighbors for Self-Supervised Learning (MNN). MNN optimizes the influence of neighbor samples on the semantics of positive samples through an intuitive weighting approach and image mixture operations. The results demonstrate that MNN exhibits exceptional generalization performance and training efficiency on four benchmark datasets.

Related papers

• A Topology-Aware Positive Sample Set Construction and Feature Optimization Method in Implicit Collaborative Filtering [40.89512526196666]
  Negative sampling strategies are widely used in implicit collaborative filtering to address issues like data sparsity and class imbalance.<n>These strategies often introduce false negatives, hindering the model's ability to accurately learn users' latent preferences.<n>We propose a Topology-aware Positive Sample Set Construction and Feature optimization method (TPSC-FO)
  arXiv  Detail & Related papers  (2026-02-20T15:35:48Z)
• Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining [64.25904019001449]
  The task of weakly supervised temporal sentence grounding (WSTSG) aims to detect temporal intervals corresponding to a language description from untrimmed videos with only video-level video-language correspondence.<n>For an anchor sample, most existing approaches generate negative samples either from other videos or within the same video for contrastive learning.<n>We propose Positive Sample Mining (PSM), a novel framework that mines positive samples from the training set to provide more discriminative supervision.
  arXiv  Detail & Related papers  (2025-05-10T08:03:00Z)
• Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning [27.278097015083343]
  Contrastive learning requires negative samples to prevent model collapse and learn discriminative representations. We introduce a cross-attention module to predict the supportiveness score of a neighbor with respect to the anchor node. Our method mitigates class collision from negative and noisy positive samples, concurrently enhancing intra-class compactness.
  arXiv  Detail & Related papers  (2024-08-09T14:17:52Z)
• Task-oriented Embedding Counts: Heuristic Clustering-driven Feature Fine-tuning for Whole Slide Image Classification [1.292108130501585]
  We propose a clustering-driven feature fine-tuning method (HC-FT) to enhance the performance of multiple instance learning. The proposed method is evaluated on both CAMELYON16 and BRACS datasets, achieving an AUC of 97.13% and 85.85%, respectively.
  arXiv  Detail & Related papers  (2024-06-02T08:53:45Z)
• Propensity Score Alignment of Unpaired Multimodal Data [3.8373578956681555]
  Multimodal representation learning techniques typically rely on paired samples to learn common representations. This paper presents an approach to address the challenge of aligning unpaired samples across disparate modalities in multimodal representation learning.
  arXiv  Detail & Related papers  (2024-04-02T02:36:21Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learning [76.00798972439004]
  Collaborative Sample Selection (CSS) removes noisy samples from identified clean set. We introduce a co-training mechanism with a contrastive loss in semi-supervised learning.
  arXiv  Detail & Related papers  (2023-10-24T05:37:20Z)
• Decoupled Contrastive Multi-View Clustering with High-Order Random Walks [25.03805821839733]
  We propose a novel robust method dubbed decoupled contrastive multi-view clustering with high-order random walks (DIVIDE) In brief, DIVIDE leverages random walks to progressively identify data pairs in a global instead of local manner. DIVIDE could identify in-neighborhood negatives and out-of-neighborhood positives.
  arXiv  Detail & Related papers  (2023-08-22T03:45:13Z)
• Contrastive Attraction and Contrastive Repulsion for Representation Learning [131.72147978462348]
  Contrastive learning (CL) methods learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples. Recent CL methods have achieved promising results when pretrained on large-scale datasets, such as ImageNet. We propose a doubly CL strategy that separately compares positive and negative samples within their own groups, and then proceeds with a contrast between positive and negative groups.
  arXiv  Detail & Related papers  (2021-05-08T17:25:08Z)
• Doubly Contrastive Deep Clustering [135.7001508427597]
  We present a novel Doubly Contrastive Deep Clustering (DCDC) framework, which constructs contrastive loss over both sample and class views. Specifically, for the sample view, we set the class distribution of the original sample and its augmented version as positive sample pairs. For the class view, we build the positive and negative pairs from the sample distribution of the class. In this way, two contrastive losses successfully constrain the clustering results of mini-batch samples in both sample and class level.
  arXiv  Detail & Related papers  (2021-03-09T15:15:32Z)
• Explaining and Improving Model Behavior with k Nearest Neighbor Representations [107.24850861390196]
  We propose using k nearest neighbor representations to identify training examples responsible for a model's predictions. We show that kNN representations are effective at uncovering learned spurious associations. Our results indicate that the kNN approach makes the finetuned model more robust to adversarial inputs.
  arXiv  Detail & Related papers  (2020-10-18T16:55:25Z)
• Understanding Negative Sampling in Graph Representation Learning [87.35038268508414]
  We show that negative sampling is as important as positive sampling in determining the optimization objective and the resulted variance. We propose Metropolis-Hastings (MCNS) to approximate the positive distribution with self-contrast approximation and accelerate negative sampling by Metropolis-Hastings. We evaluate our method on 5 datasets that cover extensive downstream graph learning tasks, including link prediction, node classification and personalized recommendation.
  arXiv  Detail & Related papers  (2020-05-20T06:25:21Z)

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.