mlsanityData to 7 Oct 2026

OASIC: Occlusion-Agnostic and Severity-Informed Classification

arXiv 2604.04012 ↗First posted 5 Apr 2026cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Severe occlusions of objects pose a major challenge for computer vision. We show that two root causes are (1) the loss of visible information and (2) the distracting patterns caused by the occluders. Our approach addresses both causes at the same time. First, the distracting patterns are removed at test-time, via masking of the occluding patterns. This masking is independent of the type of occlusion, by handling the occlusion through the lens of visual anomalies w.r.t. the object of interest. Second, to deal with less visual details, we follow standard practice by masking random parts of the object during training, for various degrees of occlusions. We discover that (a) it is possible to estimate the degree of the occlusion (i.e. severity) at test-time, and (b) that a model optimized for a specific degree of occlusion also performs best on a similar degree during test-time. Combining these two insights brings us to a severity-informed classification model called OASIC: Occlusion Agnostic Severity Informed Classification. We estimate the severity of occlusion for a test image, mask the occluder, and select the model that is optimized for the degree of occlusion. This strategy performs better than any single model optimized for any smaller or broader range of occlusion severities. Experiments show that combining gray masking with adaptive model selection improves AUCocc by +18.5 over standard training on occluded images and +23.7 over finetuning on unoccluded images.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 5 Apr 2026.

Builds on

21 of 32 references.

References · 21

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023Segment Anythingcited by 8,158
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  8. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  9. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
  10. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  11. 2022Open-Vocabulary Semantic Segmentation with Mask-adapted CLIPcited by 560
  12. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
9 more
  1. 2021Intriguing Properties of Vision Transformerscited by 446
  2. 2017Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localizationcited by 207
  3. 2020Eigen-CAM: Class Activation Map using Principal Componentscited by 188
  4. 2021TransMix: Attend to Mix for Vision Transformerscited by 79
  5. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2cited by 53
  6. 2022Understanding Masked Image Modeling via Learning Occlusion Invariant Featurecited by 50
  7. 2020Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusioncited by 47
  8. 2024Performance and Non-adversarial Robustness of the Segment Anything Model 2 in Surgical Video Segmentationcited by 13
  9. 2024Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?cited by 5

Built on by

Not cited yet.