Metric Learning with Progressive Self-Distillation for Audio-Visual Embedding Learning

• URL: http://arxiv.org/abs/2501.09608v1
• Date: Thu, 16 Jan 2025 15:32:41 GMT
• Title: Metric Learning with Progressive Self-Distillation for Audio-Visual Embedding Learning
• Authors: Donghuo Zeng, Kazushi Ikeda,
• Abstract summary: Metric learning projects samples into an embedded space, where similarities and dissimilarities are quantified. We propose a novel architecture that integrates cross-modal triplet loss with progressive self-distillation. We distill audio-visual distribution-based knowledge from annotated labels in a subset of each batch.
• Score: 2.6790916541909437
• License:
• Abstract: Metric learning projects samples into an embedded space, where similarities and dissimilarities are quantified based on their learned representations. However, existing methods often rely on label-guided representation learning, where representations of different modalities, such as audio and visual data, are aligned based on annotated labels. This approach tends to underutilize latent complex features and potential relationships inherent in the distributions of audio and visual data that are not directly tied to the labels, resulting in suboptimal performance in audio-visual embedding learning. To address this issue, we propose a novel architecture that integrates cross-modal triplet loss with progressive self-distillation. Our method enhances representation learning by leveraging inherent distributions and dynamically refining soft audio-visual alignments -- probabilistic alignments between audio and visual data that capture the inherent relationships beyond explicit labels. Specifically, the model distills audio-visual distribution-based knowledge from annotated labels in a subset of each batch. This self-distilled knowledge is used t

Related papers

• LINK: Adaptive Modality Interaction for Audio-Visual Video Parsing [26.2873961811614]
  We introduce a Learning Interaction method for Non-aligned Knowledge (Link) Link equilibrate the contributions of distinct modalities by dynamically adjusting their input during event prediction. We leverage the semantic information of pseudo-labels as a priori knowledge to mitigate noise from other modalities.
  arXiv  Detail & Related papers  (2024-12-30T11:23:15Z)
• Multi-Label Knowledge Distillation [86.03990467785312]
  We propose a novel multi-label knowledge distillation method. On one hand, it exploits the informative semantic knowledge from the logits by dividing the multi-label learning problem into a set of binary classification problems. On the other hand, it enhances the distinctiveness of the learned feature representations by leveraging the structural information of label-wise embeddings.
  arXiv  Detail & Related papers  (2023-08-12T03:19:08Z)
• Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser [34.19935635508947]
  We investigate the under-explored unaligned setting, where the goal is to recognize audio and visual events in a video with only weak labels observed. To enhance learning in this challenging setting, we incorporate large-scale contrastively pre-trained models as the modality teachers. A simple, effective, and generic method, termed Visual-Audio Label Elaboration (VALOR), is innovated to harvest modality labels for the training events.
  arXiv  Detail & Related papers  (2023-05-27T02:57:39Z)
• Learning with Neighbor Consistency for Noisy Labels [69.83857578836769]
  We present a method for learning from noisy labels that leverages similarities between training examples in feature space. We evaluate our method on datasets evaluating both synthetic (CIFAR-10, CIFAR-100) and realistic (mini-WebVision, Clothing1M, mini-ImageNet-Red) noise.
  arXiv  Detail & Related papers  (2022-02-04T15:46:27Z)
• Diffusion-Based Representation Learning [65.55681678004038]
  We augment the denoising score matching framework to enable representation learning without any supervised signal. In contrast, the introduced diffusion-based representation learning relies on a new formulation of the denoising score matching objective. Using the same approach, we propose to learn an infinite-dimensional latent code that achieves improvements of state-of-the-art models on semi-supervised image classification.
  arXiv  Detail & Related papers  (2021-05-29T09:26:02Z)
• Distilling Audio-Visual Knowledge by Compositional Contrastive Learning [51.20935362463473]
  We learn a compositional embedding that closes the cross-modal semantic gap. We establish a new, comprehensive multi-modal distillation benchmark on three video datasets.
  arXiv  Detail & Related papers  (2021-04-22T09:31:20Z)
• Unsupervised Sound Localization via Iterative Contrastive Learning [106.56167882750792]
  We propose an iterative contrastive learning framework that requires no data annotations. We then use the pseudo-labels to learn the correlation between the visual and audio signals sampled from the same video. Our iterative strategy gradually encourages the localization of the sounding objects and reduces the correlation between the non-sounding regions and the reference audio.
  arXiv  Detail & Related papers  (2021-04-01T07:48:29Z)
• CrowdTeacher: Robust Co-teaching with Noisy Answers & Sample-specific Perturbations for Tabular Data [8.276156981100364]
  Co-teaching methods have shown promising improvements for computer vision problems with noisy labels. Our model, CrowdTeacher, uses the idea that robustness in the input space model can improve the perturbation of the classifier for noisy labels. We showcase the boost in predictive power attained using CrowdTeacher for both synthetic and real datasets.
  arXiv  Detail & Related papers  (2021-03-31T15:09:38Z)
• COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations [32.456824945999465]
  We propose a method for learning audio representations, aligning the learned latent representations of audio and associated tags. We evaluate the quality of our embedding model, measuring its performance as a feature extractor on three different tasks.
  arXiv  Detail & Related papers  (2020-06-15T13:17:18Z)
• Unsupervised Cross-Modal Audio Representation Learning from Unstructured Multilingual Text [69.55642178336953]
  We present an approach to unsupervised audio representation learning. Based on a triplet neural network architecture, we harnesses semantically related cross-modal information to estimate audio track-relatedness. We show that our approach is invariant to the variety of annotation styles as well as to the different languages of this collection.
  arXiv  Detail & Related papers  (2020-03-27T07:37:15Z)

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.