Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation

Semantic segmentation models classify pixels into a set of known (``in-distribution'') visual classes. When deployed in an open world, the reliability of these models depends on their ability not only to classify in-distribution pixels but also to detect out-of-distribution (OoD) pixels. Historically, the poor OoD detection performance of these models has motivated the design of methods based on model re-training using synthetic training images that include OoD visual objects. Although successful, these re-trained methods have two issues: 1) their in-distribution segmentation accuracy may drop during re-training, and 2) their OoD detection accuracy does not generalise well to new contexts (e.g., country surroundings) outside the training set (e.g., city surroundings). In this paper, we mitigate these issues with: (i) a new residual pattern learning (RPL) module that assists the segmentation model to detect OoD pixels without affecting the inlier segmentation performance; and (ii) a novel context-robust contrastive learning (CoroCL) that enforces RPL to robustly detect OoD pixels among various contexts. Our approach improves by around 10\% FPR and 7\% AuPRC the previous state-of-the-art in Fishyscapes, Segment-Me-If-You-Can, and RoadAnomaly datasets. Our code is available at: https://github.com/yyliu01/RPL.

PDF Abstract

Results from the Paper


 Ranked #1 on Anomaly Detection on Road Anomaly (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Anomaly Detection Fishyscapes RPL+CoroCL AP 95.96 # 1
FPR95 0.52 # 1
Anomaly Detection Fishyscapes L&F RPL+CoroCL AP 53.99 # 2
FPR95 2.27 # 2
Anomaly Detection Road Anomaly RPL+CoroCL AP 71.61 # 1
FPR95 17.74 # 5

Methods