mlsanityData to 14 Oct 2026

InsCLR: Improving Instance Retrieval with Self-Supervision

arXiv 2112.01390 ↗First posted 2 Dec 2021cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

This work aims at improving instance retrieval with self-supervision. We find that fine-tuning using the recently developed self-supervised (SSL) learning methods, such as SimCLR and MoCo, fails to improve the performance of instance retrieval. In this work, we identify that the learnt representations for instance retrieval should be invariant to large variations in viewpoint and background etc., whereas self-augmented positives applied by the current SSL methods can not provide strong enough signals for learning robust instance-level representations. To overcome this problem, we propose InsCLR, a new SSL method that builds on the textitinstance-level contrast, to learn the intra-class invariance by dynamically mining meaningful pseudo positive samples from both mini-batches and a memory bank during training. Extensive experiments demonstrate that InsCLR achieves similar or even better performance than the state-of-the-art SSL methods on instance retrieval. Code is available at https://github.com/zeludeng/insclr.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 29 of its 41 references that are in the map. First posted on arXiv 2 Dec 2021.

Builds on

29 of 41 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  8. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  9. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  10. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  11. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  12. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
17 more
  1. 2020SCAN: Learning to Classify Images without Labelscited by 352
  2. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 309
  3. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  4. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 191
  5. 2019Learning with Average Precision: Training Image Retrieval with a Listwise Losscited by 185
  6. 2015Particular object retrieval with integral max-pooling of CNN activationscited by 161
  7. 2016Deep Image Retrieval: Learning global representations for image searchcited by 147
  8. 2019Cross-Batch Memory for Embedding Learningcited by 132
  9. 2016End-to-end Learning of Deep Visual Representations for Image Retrievalcited by 122
  10. 2016CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examplescited by 58
  11. 2016Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representationscited by 50
  12. 2018Detect-to-Retrieve: Efficient Regional Aggregation for Image Searchcited by 39
  13. 2019Local Features and Visual Words Emerge in Activationscited by 37
  14. 2020Delving into Inter-Image Invariance for Unsupervised Visual Representationscited by 37
  15. 2018Mining on Manifolds: Metric Learning without Labelscited by 36
  16. 2019Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Datasetcited by 17
  17. 2019Memory-Based Neighbourhood Embedding for Visual Recognitioncited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 3; 2025: 1; 2026: 2.

11 papers.

  1. 2024Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localizationcited by 31
  2. 2023Adaptive Sparse Pairwise Loss for Object Re-Identificationcited by 20
  3. 2022EViT: Privacy-Preserving Image Retrieval via Encrypted Vision Transformer in Cloud Computingcited by 5
  4. 2023Coarse-to-Fine: Learning Compact Discriminative Representation for Single-Stage Image Retrievalcited by 4
  5. 2023A Survey of Historical Learning: Learning Models with Learning Historycited by 3
  6. 2023Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learningcited by 3
  7. 2024Style Alignment based Dynamic Observation Method for UAV-View Geo-localizationcited by 1
  8. 2024PP-SSL : Priority-Perception Self-Supervised Learning for Fine-Grained Recognitioncited by 1
  9. 2025ConceptVAE: Self-Supervised Fine-Grained Concept Disentanglement from 2D Echocardiographiescited by 0
  10. 2026Geometric Analysis of Self-Supervised Vision Representations for Semantic Image Retrievalcited by 0
  11. 2026Temporal Preference Optimization for Unsupervised Retrievalcited by 0