mlsanityData to 14 Oct 2026

Evidential Transformers for Improved Image Retrieval

arXiv 2409.01082 ↗First posted 2 Sep 2024cs.CV cs.IR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce the Evidential Transformer, an uncertainty-driven transformer model for improved and robust image retrieval. In this paper, we make several contributions to content-based image retrieval (CBIR). We incorporate probabilistic methods into image retrieval, achieving robust and reliable results, with evidential classification surpassing traditional training based on multiclass classification as a baseline for deep metric learning. Furthermore, we improve the state-of-the-art retrieval results on several datasets by leveraging the Global Context Vision Transformer (GC ViT) architecture. Our experimental results consistently demonstrate the reliability of our approach, setting a new benchmark in CBIR in all test settings on the Stanford Online Products (SOP) and CUB-200-2011 datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 2 Sep 2024.

Builds on

22 of 38 references.

References · 22

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  5. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  6. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  7. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  8. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  9. 2022DeiT III: Revenge of the ViTcited by 419
  10. 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
  11. 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
  12. 2021Instance-level Image Retrieval using Reranking Transformerscited by 63
10 more
  1. 2016CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examplescited by 58
  2. 2023VA-DepthNet: A Variational Approach to Single Image Depth Predictioncited by 54
  3. 2020Being Bayesian about Categorical Probabilitycited by 35
  4. 2022Uncertainty-Aware Deep Multi-View Photometric Stereocited by 30
  5. 2015Deep filter banks for texture recognition, description, and segmentationcited by 19
  6. 2022BayesFormer: Transformer with Uncertainty Estimationcited by 19
  7. 2023Single Image Depth Prediction Made Better: A Multivariate Gaussian Takecited by 14
  8. 2024Stereo Risk: A Continuous Modeling Approach to Stereo Matchingcited by 6
  9. 2019Dirichlet uncertainty wrappers for actionable algorithm accuracy accountability and auditabilitycited by 3
  10. 2015Deep Convolutional Features for Image Based Retrieval and Scene Categorizationcited by 2

Built on by

Not cited yet.