paper-with-me

홈 › Papers

SOrT-ing VQA Models : Contrastive Gradient Learning for Improved Consistency

2020-10-20 · NAACL 2021 4 · Sameer Dharur, Purva Tendulkar, Dhruv Batra, Devi Parikh, Ramprasaath R. Selvaraju

Recent research in Visual Question Answering (VQA) has revealed state-of-the-art models to be inconsistent in their understanding of the world -- they answer seemingly difficult questions requiring reasoning correctly but get simpler associated sub-questions wrong. These sub-questions pertain to lower level visual concepts in the image that models ideally should understand to be able to answer the higher level question correctly. To address this, we first present a gradient-based interpretability approach to determine the questions most strongly correlated with the reasoning question on an image, and use this to evaluate VQA models on their ability to identify the relevant sub-questions needed to answer a reasoning question. Next, we propose a contrastive gradient learning based approach called Sub-question Oriented Tuning (SOrT) which encourages models to rank relevant sub-questions higher than irrelevant questions for an <image, reasoning-question> pair. We show that SOrT improves model consistency by upto 6.5% points over existing baselines, while also improving visual grounding.

📄 PDF Abstract BibTeX arXiv:2010.10038

Code (1)

sameerdharur/sorting-vqa 공식 구현 pytorch

Tasks

Question AnsweringVisual GroundingVisual Question AnsweringVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Similar Papers 제목 키워드 기반

Learning to Hash Naturally Sorts

2022-01-31 · Jiaguo Yu, Yuming Shen, Menghan Wang, Haofeng Zhang 외

Learning to hash pictures a list-wise sorting problem. Its testing metrics, e.g., mean-average precision, count on a sorted candidate list ordered by pair-wise code similarity. However, scarcely does one train a deep has…

Contrastive LearningDeep HashingRetrieval

Learning by Sorting: Self-supervised Learning with Group Ordering Constraints

2023-01-05 · ICCV 2023 1 · Nina Shvetsova, Felix Petersen, Anna Kukleva, Bernt Schiele 외

Contrastive learning has become an important tool in learning representations from unlabeled data mainly relying on the idea of minimizing distance between positive data pairs, e.g., views from the same images, and maxim…

Contrastive LearningSelf-Supervised Image ClassificationSelf-Supervised Learning

A Differentiable Ranking Metric Using Relaxed Sorting Operation for Top-K Recommender Systems

2020-08-30 · Hyunsung Lee, Yeongjae Jang, Jaekwang Kim, Honguk Woo

A recommender system generates personalized recommendations for a user by computing the preference score of items, sorting the items according to the score, and filtering top-K items with high scores. While sorting and r…

Recommendation Systems

Near, far: Patch-ordering enhances vision foundation models' scene understanding

2024-08-20 · Valentinos Pariza, Mohammadreza Salehi, Gertjan Burghouts, Francesco Locatello 외

We introduce NeCo: Patch Neighbor Consistency, a novel self-supervised training loss that enforces patch-level nearest neighbor consistency across a student and teacher model. Compared to contrastive approaches that only…

GPUScene UnderstandingSelf-Supervised LearningSemantic Segmentation

Weighted Contrastive Divergence

2018-01-08 · Enrique Romero Merino, Ferran Mazzanti Castrillejo, Jordi Delgado Pin, David Buchaca Prats

Learning algorithms for energy based Boltzmann architectures that rely on gradient descent are in general computationally prohibitive, typically due to the exponential number of terms involved in computing the partition …