mlsanityData to 7 Oct 2026

Residual Attention: A Simple but Effective Method for Multi-Label Recognition

arXiv 2108.02456 ↗First posted 5 Aug 2021cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

Multi-label image recognition is a challenging computer vision task of practical use. Progresses in this area, however, are often characterized by complicated methods, heavy computations, and lack of intuitive explanations. To effectively capture different spatial regions occupied by objects from different categories, we propose an embarrassingly simple module, named class-specific residual attention (CSRA). CSRA generates class-specific features for every category by proposing a simple spatial attention score, and then combines it with the class-agnostic average pooling feature. CSRA achieves state-of-the-art results on multilabel recognition, and at the same time is much simpler than them. Furthermore, with only 4 lines of code, CSRA also leads to consistent improvement across many diverse pretrained models and datasets without any extra training. CSRA is both easy to implement and light in computations, which also enjoys intuitive explanations and visualizations.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Builds on 26 of its 42 references that are in the map. First posted on arXiv 5 Aug 2021.

Builds on

26 of 42 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  8. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  9. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  10. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  11. 2020Asymmetric Loss For Multi-Label Classificationcited by 379
  12. 2019Multi-Label Image Recognition with Graph Convolutional Networkscited by 320
14 more
  1. 2016CNN-RNN: A Unified Framework for Multi-label Image Classificationcited by 189
  2. 2020TResNet: High Performance GPU-Dedicated Architecturecited by 119
  3. 2019Learning Semantic-Specific Graph Representation for Multi-Label Image Recognitioncited by 116
  4. 2017Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classificationcited by 85
  5. 2017Multi-label Image Recognition by Recurrently Discovering Attentional Regionscited by 83
  6. 2019Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classificationcited by 78
  7. 2014CNN: Single-label to Multi-labelcited by 62
  8. 2018Deep Imbalanced Attribute Classification using Visual Attention Aggregationcited by 56
  9. 2019ThunderNet: Towards Real-time Generic Object Detectioncited by 42
  10. 2015Exploit Bounding Box Annotations for Multi-label Object Recognitioncited by 39
  11. 2018Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detectioncited by 37
  12. 2016Multi-Label Image Classification with Regional Latent Semantic Dependenciescited by 23
  13. 2017End-to-end Flow Correlation Tracking with Spatial-temporal Attentioncited by 21
  14. 2018Deep Attentive Tracking via Reciprocative Learningcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 11; 2023: 14; 2024: 12; 2025: 10; 2026: 4.

52 papers.

Sort:

By area:

  1. 2022DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotationscited by 102
  2. 2021ML-Decoder: Scalable and Versatile Classification Headcited by 78
  3. 2022Exemplar Guided Deep Neural Network for Spatial Transcriptomics Analysis of Gene Expression Predictioncited by 39
  4. 2022Acknowledging the Unknown for Multi-label Learning with Single Positive Labelscited by 24
  5. 2023DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotationscited by 22
  6. 2023Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challengecited by 22
  7. 2023PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classificationcited by 21
  8. 2022PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detectioncited by 17
  9. 2023Multi-Label Self-Supervised Learning with Scene Imagescited by 17
  10. 2024CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representationcited by 9
  11. 2023End-to-End Supervised Multilabel Contrastive Learningcited by 8
  12. 2023Semantic-Aware Dual Contrastive Learning for Multi-label Image Classificationcited by 8
38 more
  1. 2022Semantic Representation and Dependency Learning for Multi-Label Image Recognitioncited by 6
  2. 2024The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typingcited by 6
  3. 2022Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classificationcited by 4
  4. 2023LSAS: Lightweight Sub-attention Strategy for Alleviating Attention Bias Problemcited by 4
  5. 2023SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classificationcited by 4
  6. 2025LipGen: Viseme-Guided Lip Video Generation for Enhancing Visual Speech Recognitioncited by 4
  7. 2026Handling Supervision Scarcity in Chest X-ray Classification: Long-Tailed and Zero-Shot Learningcited by 4
  8. 2022Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervisioncited by 3
  9. 2023Text as Image: Learning Transferable Adapter for Multi-Label Classificationcited by 3
  10. 2024ProbMCL: Simple Probabilistic Contrastive Learning for Multi-label Visual Classificationcited by 3
  11. 2024HSVLT: Hierarchical Scale-Aware Vision-Language Transformer for Multi-Label Image Classificationcited by 3
  12. 2024FedGCA: Global Consistent Augmentation Based Single-Source Federated Domain Generalizationcited by 3
  13. 2022PAMI-AD: An Activity Detector Exploiting Part-attention and Motion Information in Surveillance Videoscited by 2
  14. 2023Multi-view Contrastive Learning for Entity Typing over Knowledge Graphscited by 2
  15. 2024PVLR: Prompt-driven Visual-Linguistic Representation Learning for Multi-Label Image Recognitioncited by 2
  16. 2024NOAH: Learning Pairwise Object Category Attentions for Image Classificationcited by 2
  17. 2024SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognitioncited by 2
  18. 2022Learning Disentangled Label Representations for Multi-label Classificationcited by 1
  19. 2023DOST -- Domain Obedient Self-supervised Training for Multi Label Classification with Noisy Labelscited by 1
  20. 2023Learning to recognize occluded and small objects with partial inputscited by 1
  21. 2024Rethinking Prompting Strategies for Multi-Label Recognition with Partial Annotationscited by 1
  22. 2022Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognitioncited by 0
  23. 2022Food Ingredients Recognition through Multi-label Learningcited by 0
  24. 2023Multi-Label Noise Transition Matrix Estimation with Label Correlations: Theory and Algorithmcited by 0
  25. 2023Dual Feature Augmentation Network for Generalized Zero-shot Learningcited by 0
  26. 2024Modeling Weather Uncertainty for Multi-weather Co-Presence Estimationcited by 0
  27. 2024Towards Enhanced Classification of Abnormal Lung sound in Multi-breath: A Light Weight Multi-label and Multi-head Attention Classification Methodcited by 0
  28. 2024Modeling Multi-modal Cross-interaction for Multi-label Few-shot Image Classification Based on Local Feature Selectioncited by 0
  29. 2025Intelligent Diagnosis Using Dual-Branch Attention Network for Rare Thyroid Carcinoma Recognition with Ultrasound Imagingcited by 0
  30. 2025Attack Smarter: Attention-Driven Fine-Grained Webpage Fingerprinting Attackscited by 0
  31. 2025Self-Supervised Contrastive Learning for Multi-Label Imagescited by 0
  32. 2025Multi-Label Classification Framework for Hurricane Damage Assessmentcited by 0
  33. 2025Semantic-Aware Representation Learning via Conditional Transport for Multi-Label Image Classificationcited by 0
  34. 2025Information Bottleneck-based Causal Attention for Multi-label Medical Image Recognitioncited by 0
  35. 2025MCANet: A Multi-Scale Class-Specific Attention Network for Multi-Label Post-Hurricane Damage Assessment Using UAV Imagerycited by 0
  36. 2025Incomplete Multi-Label Image Recognition by Co-learning Semantic-Aware Features and Label Recoverycited by 0
  37. 2025Supervised Multilabel Image Classification Using Residual Networks with Probabilistic Reasoningcited by 0
  38. 2026Rethinking Multi-Label Image Classification With Deep Learning: Taxonomy, Challenge, and Outlookcited by 0

50 most cited of 52 All 52 (JSON)