REVIEW 2 cited by
WeaQA: Weak Supervision via Captions for Visual Question Answering
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
Methodologies for training visual question answering (VQA) models assume the availability of datasets with human-annotated \textit{Image-Question-Answer} (I-Q-A) triplets. This has led to heavy reliance on datasets and a lack of generalization to new types of questions and scenes. Linguistic priors along with biases and errors due to annotator subjectivity have been shown to percolate into VQA models trained on such samples. We study whether models can be trained without any human-annotated Q-A pairs, but only with images and their associated textual descriptions or captions. We present a method to train models with synthetic Q-A pairs generated procedurally from captions. Additionally, we demonstrate the efficacy of spatial-pyramid image patches as a simple but effective alternative to dense and costly object bounding box annotations used in existing VQA models. Our experiments on three VQA benchmarks demonstrate the efficacy of this weakly-supervised approach, especially on the VQA-CP challenge, which tests performance under changing linguistic priors.
Forward citations
Cited by 2 Pith papers
-
Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos
LangView uses per-view caption accuracy against view-agnostic narrations as pseudo-labels to train a view selector that outperforms heuristics and prior baselines on Ego-Exo4D and LEMMA.
-
RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation
A rule-guided spatial-aware network that localizes all mentioned entities in a 3D scene and uses target-position weak supervision raises ScanRefer 3D-RES mIoU from 39.5 to 44.6.
Discussion (0). Continue with ORCID to comment.