Barbara Caputo, Carlo Masone, Politecnico Torino, Fabio Cermelli, Dario Fontanel, Shyam Rai
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Anomaly segmentation is a critical task for driving applications, and it is approached traditionally as a perpixel classification problem. However, reasoning individually about each pixel without considering their contextual semantics results in high uncertainty around the objects' boundaries and numerous false positives. We propose a paradigm change by shifting from a per-pixel classification to a mask classification. Our mask-based method, Mask2Anomaly, demonstrates the feasibility of integrating an anomaly detection method in a mask-classification architecture. Mask2Anomaly includes several technical novelties that are designed to improve the detection of anomalies in masks: i) a global masked attention module to focus individually on the foreground and background regions; ii) a mask contrastive learning that maximizes the margin between an anomaly and known classes; and iii) a mask refinement solution to reduce false positives. Mask2Anomaly achieves new state-of-the-art results across a range of benchmarks, both in the per-pixel and component-level evaluations. In particular, Mask2Anomaly reduces the average false positives rate by 60% w.r.t. the previous stateof-the-art.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2307.13316")
get_code_for_paper("2307.13316")
have("2307.13316")
Connect an agent — have() is free.