Papers
arxiv:2604.21349

Trust-SSL: Additive-Residual Selective Invariance for Robust Aerial Self-Supervised Learning

Published on Apr 23
Authors:
,

Abstract

A novel self-supervised learning approach enhances robustness to image corruptions by introducing per-sample trust weights in the alignment objective, achieving superior performance on aerial imagery datasets.

AI-generated summary

Self-supervised learning (SSL) is a standard approach for representation learning in aerial imagery. Existing methods enforce invariance between augmented views, which works well when augmentations preserve semantic content. However, aerial images are frequently degraded by haze, motion blur, rain, and occlusion that remove critical evidence. Enforcing alignment between a clean and a severely degraded view can introduce spurious structure into the latent space. This study proposes a training strategy and architectural modification to enhance SSL robustness to such corruptions. It introduces a per-sample, per-factor trust weight into the alignment objective, combined with the base contrastive loss as an additive residual. A stop-gradient is applied to the trust weight instead of a multiplicative gate. While a multiplicative gate is a natural choice, experiments show it impairs the backbone, whereas our additive-residual approach improves it. Using a 200-epoch protocol on a 210,000-image corpus, the method achieves the highest mean linear-probe accuracy among six backbones on EuroSAT, AID, and NWPU-RESISC45 (90.20% compared to 88.46% for SimCLR and 89.82% for VICReg). It yields the largest improvements under severe information-erasing corruptions on EuroSAT (+19.9 points on haze at s=5 over SimCLR). The method also demonstrates consistent gains of +1 to +3 points in Mahalanobis AUROC on a zero-shot cross-domain stress test using BDD100K weather splits. Two ablations (scalar uncertainty and cosine gate) indicate the additive-residual formulation is the primary source of these improvements. An evidential variant using Dempster-Shafer fusion introduces interpretable signals of conflict and ignorance. These findings offer a concrete design principle for uncertainty-aware SSL. Code is publicly available at https://github.com/WadiiBoulila/trust-ssl.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2604.21349
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2604.21349 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2604.21349 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2604.21349 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.