Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet · HackerPapers discussions

Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet — mentioned by sarosh

Sun, 06 Dec 2020 15:39:13 GMT

See also W. Brendel and M. Bethge. "Approximating CNNs with bag-of-local-features models works surprisingly well on ImageNet." https://arxiv.org/abs/1904.00760 (which is referenced in this paper) and explains "[t]his suggests that the improvements of DNNs over previous bag-of-feature classifiers in the last few years is mostly achieved by better fine-tuning rather than by qualitatively different decision strategies."

Paper and discussion history. A mention is not an endorsement.

Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet — mentioned by b3kart

Wed, 05 Feb 2020 17:27:15 GMT

I am not convinced the explanations we’d get from these models would be interpretable enough to drive their conceptual improvement. Deep nets just don’t learn nice interpretable features, nothing in the training objective makes them do so. E.g. they make use of really dubious features [1], and might not actually learn “hierarchies” of features as we thought they were [2]. [1] https://arxiv.org/abs/1905.02175 [2] https://arxiv.org/abs/1904.00760

Paper and discussion history. A mention is not an endorsement.