Learning Deep Features for Discriminative Localization
read the original abstract
In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels. While this technique was previously proposed as a means for regularizing training, we find that it actually builds a generic localizable deep representation that can be applied to a variety of tasks. Despite the apparent simplicity of global average pooling, we are able to achieve 37.1% top-5 error for object localization on ILSVRC 2014, which is remarkably close to the 34.2% top-5 error achieved by a fully supervised CNN approach. We demonstrate that our network is able to localize the discriminative image regions on a variety of tasks despite not being trained for them
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Wavelet-Based Extraction of Transient Noise in Gravitational-Wave Interferometers using a Saliency-Guided Learning Architecture
A saliency-guided wavelet framework extracts transient glitches from gravitational-wave strain data by pre-tagging candidates with UMAP, identifying time-frequency regions on CWT spectrograms, and enabling exact recon...
-
Rare Events, Real Signals: Functional Ensembles as Units of Computation in Deep Spiking Networks
In spiking ResNets, 1FC ensembles defined by pairwise correlations show ReLU-like cofiring-to-response mapping whose gain scales with ensemble size, with reliable class encoding restricted to infrequent high-cofiring events.
-
Investigation of cardinality classification for bacterial colony counting using explainable artificial intelligence
XAI analysis identifies high visual similarity across colony cardinality classes as the primary limit on MicrobiaNet performance in bacterial colony counting, revising prior model assessments.
-
Deep Reinforcement Learning for Spacecraft Attitude Control During Atmospheric Re-Entry
Hybrid RL-PID controllers track angle of attack better and show greater robustness than PID alone within a defined operational envelope for re-entry attitude control.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.