REVIEW 3 cited by
Multi-Task Incremental Learning for Object Detection
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Multi-task learns multiple tasks, while sharing knowledge and computation among them. However, it suffers from catastrophic forgetting of previous knowledge when learned incrementally without access to the old data. Most existing object detectors are domain-specific and static, while some are learned incrementally but only within a single domain. Training an object detector incrementally across various domains has rarely been explored. In this work, we propose three incremental learning scenarios across various domains and categories for object detection. To mitigate catastrophic forgetting, attentive feature distillation is proposed to leverages both bottom-up and top-down attentions to extract important information for distillation. We then systematically analyze the proposed distillation method in different scenarios. We find out that, contrary to common understanding, domain gaps have smaller negative impact on incremental detection, while category differences are problematic. For the difficult cases, where the domain gaps and especially category differences are large, we explore three different exemplar sampling methods and show the proposed adaptive sampling method is effective to select diverse and informative samples from entire datasets, to further prevent forgetting. Experimental results show that we achieve the significant improvement in three different scenarios across seven object detection benchmark datasets.
Forward citations
Cited by 3 Pith papers
-
Class-Incremental Motion Forecasting
OMEN is the first end-to-end class-incremental motion forecaster that retains old-class accuracy via VLM-filtered future-detection pseudo-labels and variance-based sequence replay.
-
DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic
DuET is an exemplar-free task-arithmetic model-merging framework that performs simultaneous class- and domain-incremental object detection, validated on YOLO11 and RT-DETR, with a new directional consistency loss and ...
-
Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need
SOYO is a lightweight trainable domain selector for parameter-isolation domain incremental learning, improving parameter selection accuracy and downstream performance on six benchmarks.
Discussion (0). Continue with ORCID to comment.