DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition

• URL: http://arxiv.org/abs/2404.14890v1
• Date: Tue, 23 Apr 2024 10:17:42 GMT
• Title: DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition
• Authors: Haozhe Cheng, Cheng Ju, Haicheng Wang, Jinxiang Liu, Mengting Chen, Qiang Hu, Xiaoyun Zhang, Yanfeng Wang,
• Abstract summary: Open-Vocabulary Action Recognition (OVAR) is one of the fundamental video tasks in computer vision. This paper pioneers to evaluate existing methods by simulating multi-level noises of various types. We propose one novel DENOISER framework, covering two parts: generation and discrimination.
• Score: 28.02038637078298
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As one of the fundamental video tasks in computer vision, Open-Vocabulary Action Recognition (OVAR) recently gains increasing attention, with the development of vision-language pre-trainings. To enable generalization of arbitrary classes, existing methods treat class labels as text descriptions, then formulate OVAR as evaluating embedding similarity between visual samples and textual classes. However, one crucial issue is completely ignored: the class descriptions given by users may be noisy, e.g., misspellings and typos, limiting the real-world practicality of vanilla OVAR. To fill the research gap, this paper pioneers to evaluate existing methods by simulating multi-level noises of various types, and reveals their poor robustness. To tackle the noisy OVAR task, we further propose one novel DENOISER framework, covering two parts: generation and discrimination. Concretely, the generative part denoises noisy class-text names via one decoding process, i.e., propose text candidates, then utilize inter-modal and intra-modal information to vote for the best. At the discriminative part, we use vanilla OVAR models to assign visual samples to class-text names, thus obtaining more semantics. For optimization, we alternately iterate between generative and discriminative parts for progressive refinements. The denoised text classes help OVAR models classify visual samples more accurately; in return, classified visual samples help better denoising. On three datasets, we carry out extensive experiments to show our superior robustness, and thorough ablations to dissect the effectiveness of each component.

Related papers

• Self-Ensemble Post Learning for Noisy Domain Generalization [18.4218677759831]
  This paper explores how to make existing methods rework when meeting noise.<n>We find that the latent features inside the model have certain discriminative capabilities.<n>We propose the Self-Ensemble Post Learning approach to diversify features which can be leveraged.
  arXiv  Detail & Related papers  (2025-12-11T17:09:35Z)
• Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning [23.129998055266245]
  Current pseudo-labeling strategies often struggle with mismatches between semantic and visual information. We introduce a simple yet effective approach called textbfAugmenting Dtextbfiscriminative textbfRichness via Diffusions (AiR)
  arXiv  Detail & Related papers  (2025-04-16T10:09:45Z)
• Label-template based Few-Shot Text Classification with Contrastive Learning [7.964862748983985]
  We propose a simple and effective few-shot text classification framework. Label templates are embedded into input sentences to fully utilize the potential value of class labels. supervised contrastive learning is utilized to model the interaction information between support samples and query samples.
  arXiv  Detail & Related papers  (2024-12-13T12:51:50Z)
• Beyond Coarse-Grained Matching in Video-Text Retrieval [50.799697216533914]
  We introduce a new approach for fine-grained evaluation. Our approach can be applied to existing datasets by automatically generating hard negative test captions. Experiments on our fine-grained evaluations demonstrate that this approach enhances a model's ability to understand fine-grained differences.
  arXiv  Detail & Related papers  (2024-10-16T09:42:29Z)
• Towards Generative Class Prompt Learning for Fine-grained Visual Recognition [5.633314115420456]
  Generative Class Prompt Learning and Contrastive Multi-class Prompt Learning are presented. Generative Class Prompt Learning improves visio-linguistic synergy in class embeddings by conditioning on few-shot exemplars with learnable class prompts. CoMPLe builds on this foundation by introducing a contrastive learning component that encourages inter-class separation.
  arXiv  Detail & Related papers  (2024-09-03T12:34:21Z)
• Diversified in-domain synthesis with efficient fine-tuning for few-shot classification [64.86872227580866]
  Few-shot image classification aims to learn an image classifier using only a small set of labeled examples per class. We propose DISEF, a novel approach which addresses the generalization challenge in few-shot learning using synthetic data. We validate our method in ten different benchmarks, consistently outperforming baselines and establishing a new state-of-the-art for few-shot classification.
  arXiv  Detail & Related papers  (2023-12-05T17:18:09Z)
• CAPro: Webly Supervised Learning with Cross-Modality Aligned Prototypes [93.71909293023663]
  Cross-modality Aligned Prototypes (CAPro) is a unified contrastive learning framework to learn visual representations with correct semantics. CAPro achieves new state-of-the-art performance and exhibits robustness to open-set recognition.
  arXiv  Detail & Related papers  (2023-10-15T07:20:22Z)
• Diffusion Models for Open-Vocabulary Segmentation [79.02153797465324]
  OVDiff is a novel method that leverages generative text-to-image diffusion models for unsupervised open-vocabulary segmentation. It relies solely on pre-trained components and outputs the synthesised segmenter directly, without training.
  arXiv  Detail & Related papers  (2023-06-15T17:51:28Z)
• Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models [44.60439935450292]
  We propose a novel method for zero-shot visual recognition: RECODE. It decomposes each predicate category into subject, object, and spatial components. Different visual cues enhance the discriminability of similar relation categories from different perspectives.
  arXiv  Detail & Related papers  (2023-05-21T14:40:48Z)
• Text2Model: Text-based Model Induction for Zero-shot Image Classification [38.704831945753284]
  We address the challenge of building task-agnostic classifiers using only text descriptions. We generate zero-shot classifiers using a hypernetwork that receives class descriptions and outputs a multi-class model. We evaluate this approach in a series of zero-shot classification tasks, for image, point-cloud, and action recognition, using a range of text descriptions.
  arXiv  Detail & Related papers  (2022-10-27T05:19:55Z)
• Context-based Virtual Adversarial Training for Text Classification with Noisy Labels [1.9508698179748525]
  We propose context-based virtual adversarial training (ConVAT) to prevent a text classifier from overfitting to noisy labels. Unlike the previous works, the proposed method performs the adversarial training at the context level rather than the inputs. We conduct extensive experiments on four text classification datasets with two types of label noises.
  arXiv  Detail & Related papers  (2022-05-29T14:19:49Z)
• Dense Contrastive Visual-Linguistic Pretraining [53.61233531733243]
  Several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining. We propose unbiased Dense Contrastive Visual-Linguistic Pretraining to replace the region regression and classification with cross-modality region contrastive learning.
  arXiv  Detail & Related papers  (2021-09-24T07:20:13Z)
• Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches [52.67723703088284]
  We propose a novel framework called multi-patch generative adversarial nets (MPGAN) MPGAN synthesises local patch features and labels unseen classes with a novel weighted voting strategy. MPGAN has significantly greater accuracy than state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-27T05:49:44Z)

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.