REVIEW 2 cited by
Optimized Generic Feature Learning for Few-shot Classification across Domains
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
To learn models or features that generalize across tasks and domains is one of the grand goals of machine learning. In this paper, we propose to use cross-domain, cross-task data as validation objective for hyper-parameter optimization (HPO) to improve on this goal. Given a rich enough search space, optimization of hyper-parameters learn features that maximize validation performance and, due to the objective, generalize across tasks and domains. We demonstrate the effectiveness of this strategy on few-shot image classification within and across domains. The learned features outperform all previous few-shot and meta-learning approaches.
Forward citations
Cited by 2 Pith papers
-
Few-shot Classification as Multi-instance Verification: Effective Backbone-agnostic Transfer across Domains
A test-time trained 'MIV-head' turns few-shot classification into a series of multi-instance verification tasks and reaches accuracy competitive with adapter-based fine-tuning on frozen backbones.
-
Reliable Few-shot Learning under Dual Noises
DETA++ combines region-weighting, noise-entropy maximization, memory-bank prototypes, and intra-class region swapping to handle both in-distribution and out-of-distribution noise in few-shot learning.
Discussion (0). Sign in to comment.