Papers › On Generalizing Detection Models for Unconstrained Environments

On Generalizing Detection Models for Unconstrained Environments

28 Sep 2019arXiv:1909.13080archive 2025-07-28

Prajjwal Bhargava

Object detection has seen tremendous progress in recent years. However, current algorithms don't generalize well when tested on diverse data distributions. We address the problem of incremental learning in object detection on the India Driving Dataset (IDD). Our approach involves using multiple domain-specific classifiers and effective transfer learning techniques focussed on avoiding catastrophic forgetting. We evaluate our approach on the IDD and BDD100K dataset. Results show the effectiveness of our domain adaptive approach in the case of domain shifts in environments.

PaperPDFCode

Code

prajjwal1/autonomous-object-detection officialmentioned in papermentioned on GitHubpytorchMIT 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

Incremental LearningObjectObject DetectionTransfer Learningobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection BDD100K val hybrid incremental net mAP@0.5 45.7 #1 of 1 Archive leaderboard report
Object Detection India Driving Dataset hybrid incremental net mAP@0.5 31.57 #2 of 4 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