Methods › Computer Vision › Vision Transformers › OODformer

OODformer

1 paper tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

OODformer is a transformer-based OOD detection architecture that leverages the contextualization capabilities of the transformer. Incorporating the transformer as the principal feature extractor allows to exploit the object concepts and their discriminate attributes along with their co-occurrence via visual attention.

OODformer employs ViT and its data efficient variant DeiT. Each encoder layer consist of multi-head self attention and a multi-layer perception block. The combination of MSA and MLP layers in the encoder jointly encode the attributes' importance, associated correlation, and co-occurrence. The [class] token (a representative of an image x) consolidated multiple attributes and their related features via the global context. The [class] token from the final layer is used for OOD detection in two ways; first, it is passed to F_(classifier)(x_(feat)) for softmax confidence score, and second it is used for latent space distance calculation.

Source: OODformer: Out-Of-Distribution Detection Transformer

Papers archive 2025-07-28

1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Contrastive Learning1
Image Classification1
Out of Distribution (OOD) Detection1
Out-of-Distribution Detection1
image-classification1

Usage over time archive 2025-07-28

Papers per year tagged with OODformer: 2021 to 2021, peak 1 1 0 2021: 1 paper 2021
Papers per year the archive tags with this method, by the paper's archive date (1 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Vision Transformers

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections