REVIEW 5 cited by
Open-Set Recognition: a Good Closed-Set Classifier is All You Need?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The ability to identify whether or not a test sample belongs to one of the semantic classes in a classifier's training set is critical to practical deployment of the model. This task is termed open-set recognition (OSR) and has received significant attention in recent years. In this paper, we first demonstrate that the ability of a classifier to make the 'none-of-above' decision is highly correlated with its accuracy on the closed-set classes. We find that this relationship holds across loss objectives and architectures, and further demonstrate the trend both on the standard OSR benchmarks as well as on a large-scale ImageNet evaluation. Second, we use this correlation to boost the performance of a maximum logit score OSR 'baseline' by improving its closed-set accuracy, and with this strong baseline achieve state-of-the-art on a number of OSR benchmarks. Similarly, we boost the performance of the existing state-of-the-art method by improving its closed-set accuracy, but the resulting discrepancy with the strong baseline is marginal. Our third contribution is to present the 'Semantic Shift Benchmark' (SSB), which better respects the task of detecting semantic novelty, in contrast to other forms of distribution shift also considered in related sub-fields, such as out-of-distribution detection. On this new evaluation, we again demonstrate that there is negligible difference between the strong baseline and the existing state-of-the-art. Project Page: https://www.robots.ox.ac.uk/~vgg/research/osr/
Forward citations
Cited by 5 Pith papers
-
MedXplore: Towards Reliable and Unbiased Generalized Category Discovery in Medical Imaging
A frequency-based attention module plus adaptive margins raises generalized category discovery accuracy on four medical imaging benchmarks by an average of 8.5 points over prior methods.
-
A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention
Attention Focusing, a token-pruning module, improves Generalized Category Discovery accuracy on seven datasets by making models focus on informative image regions.
-
SODA: Out-of-Distribution Detection in Domain-Shifted Point Clouds via Neighborhood Propagation
A training-free neighborhood score propagation method improves out-of-distribution detection for point clouds under synthetic-to-real domain shift.
-
Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation
A CLIP-based method that searches WordNet nouns as target semantic centers in text-embedding space and uses information maximization for alignment achieves state-of-the-art Universal Domain Adaptation on four benchmarks.
-
Prior-Constrained Association Learning for Fine-Grained Generalized Category Discovery
A prior-constrained greedy association algorithm, combined with prototypical contrastive learning, sets new state-of-the-art results on fine-grained generalized category discovery.
Discussion (0). Continue with ORCID to comment.