Papers › Contextual Classification Using Self-Supervised Auxiliary Models for Deep Neural Networks

Contextual Classification Using Self-Supervised Auxiliary Models for Deep Neural Networks

7 Jan 2021arXiv:2101.03057archive 2025-07-28

Sebastian Palacio, Philipp Engler, Jörn Hees, Andreas Dengel

Classification problems solved with deep neural networks (DNNs) typically rely on a closed world paradigm, and optimize over a single objective (e.g., minimization of the cross-entropy loss). This setup dismisses all kinds of supporting signals that can be used to reinforce the existence or absence of a particular pattern. The increasing need for models that are interpretable by design makes the inclusion of said contextual signals a crucial necessity. To this end, we introduce the notion of Self-Supervised Autogenous Learning (SSAL) models. A SSAL objective is realized through one or more additional targets that are derived from the original supervised classification task, following architectural principles found in multi-task learning. SSAL branches impose low-level priors into the optimization process (e.g., grouping). The ability of using SSAL branches during inference, allow models to converge faster, focusing on a richer set of class-relevant features. We show that SSAL models consistently outperform the state-of-the-art while also providing structured predictions that are more interpretable.

Paper PDF Code

Code

Engler93/Self-Supervised-Autogenous-Learning officialpytorch 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.

Code Syntology ran Syntology

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

Tasks

General Classification Image Classification Multi-Task Learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Image Classification	CIFAR-100	SSAL-DenseNet 190-40	Percentage correct	83.2	#90 of 211	Archive leaderboard	report
Image Classification	ImageNet	SSAL-Resnet50	Top 1 Accuracy	77.0%	#890 of 1060	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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