Papers › CNN Features off-the-shelf: an Astounding Baseline for Recognition

CNN Features off-the-shelf: an Astounding Baseline for Recognition

23 Mar 2014arXiv:1403.6382archive 2025-07-28

Ali Sharif Razavian, Hossein Azizpour, Josephine Sullivan, Stefan Carlsson

Recent results indicate that the generic descriptors extracted from the convolutional neural networks are very powerful. This paper adds to the mounting evidence that this is indeed the case. We report on a series of experiments conducted for different recognition tasks using the publicly available code and model of the \overfeat network which was trained to perform object classification on ILSVRC13. We use features extracted from the \overfeat network as a generic image representation to tackle the diverse range of recognition tasks of object image classification, scene recognition, fine grained recognition, attribute detection and image retrieval applied to a diverse set of datasets. We selected these tasks and datasets as they gradually move further away from the original task and data the \overfeat network was trained to solve. Astonishingly, we report consistent superior results compared to the highly tuned state-of-the-art systems in all the visual classification tasks on various datasets. For instance retrieval it consistently outperforms low memory footprint methods except for sculptures dataset. The results are achieved using a linear SVM classifier (or L2 distance in case of retrieval) applied to a feature representation of size 4096 extracted from a layer in the net. The representations are further modified using simple augmentation techniques e.g. jittering. The results strongly suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Aniket7/Transfer-Learning mentioned on GitHubSyntology: not harvested report
baldassarreFe/deep-koalarization mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Colorful Image Colorization (arXiv:1603.08511; that paper's own run record: 47 ran (of which 10 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 17 where Syntology's instrument failed) · 26 unverified); nothing checks that they implement this paper's method. report
jimgoo/caffe-oxford102 mentioned on GitHubSyntology: not harvested report
joshuaczhao/CNN-Sentence-Classifier-Reproduction mentioned on GitHubtfSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AttributeGeneral ClassificationImage ClassificationImage RetrievalRetrievalScene Recognitionimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SVM

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