# Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-Time Source: [Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-Time]() Collection index: [llms.txt]() Data updated: 2025-10-26T03:24:17.272Z Authors: Chiao-An Yang, Ziwei Liu, Raymond A. Yeh Published: 2024-10-01T21:24:43.000Z ## Abstract Subsampling layers play a crucial role in deep nets by discarding a portion of an activation map to reduce its spatial dimensions. This encourages the deep net to learn higher-level representations. Contrary to this motivation, we hypothesize that the discarded activations are useful and can be incorporated on the fly to improve models' prediction. To validate our hypothesis, we propose a search and aggregate method to find useful activation maps to be used at test time. We applied our approach to the task of image classification and semantic segmentation. Extensive experiments over nine different architectures on multiple datasets show that our method consistently improves model test-time performance, complementing existing test-time augmentation techniques. Our code is available at https://github.com/ca-joe-yang/discard-in-subsampling. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()