paper-with-me

Papers

Interpretable Visual Reasoning via Probabilistic Formulation under Natural Supervision

2020-08-01 · ECCV 2020 8 · Xinzhe Han, Shuhui Wang, Chi Su, Weigang Zhang, Qingming Huang, Qi Tian

Visual reasoning is crucial for visual question answering (VQA). However, without labelled programs, implicit reasoning under natural supervision is still quite challenging and previous models are hard to interpret. In this paper, we rethink implicit reasoning process in VQA, and propose a new formulation which maximizes the log-likelihood of joint distribution for the observed question and predicted answer. Accordingly, we derive a Temporal Reasoning Network (TRN) framework which models the implicit reasoning process as sequential planning in latent space. Our model is interpretable on both model design in probabilist and reasoning process via visualization. We experimentally demonstrate that TRN can support implicit reasoning across various datasets. The experiment results of our model are competitive to existing implicit reasoning models and surpass baseline by large margin on complicated reasoning tasks without extra computation cost in forward stage.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)Visual Reasoning

Similar Papers 제목 키워드 기반

Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering

2019-02-21 · ICLR 2019 5 · Ramakrishna Vedantam, Karan Desai, Stefan Lee, Marcus Rohrbach 외

We propose a new class of probabilistic neural-symbolic models, that have symbolic functional programs as a latent, stochastic variable. Instantiated in the context of visual question answering, our probabilistic formula…

counterfactualQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures

2024-01-29 · Michael Hersche, Francesco Di Stefano, Thomas Hofmann, Abu Sebastian 외

Abstract reasoning is a cornerstone of human intelligence, and replicating it with artificial intelligence (AI) presents an ongoing challenge. This study focuses on efficiently solving Raven's progressive matrices (RPM),…

Attribute

PRIMEDrive-CoT: A Precognitive Chain-of-Thought Framework for Uncertainty-Aware Object Interaction in Driving Scene Scenario

2025-04-08 · Sriram Mandalika, Lalitha V, Athira Nambiar

Driving scene understanding is a critical real-world problem that involves interpreting and associating various elements of a driving environment, such as vehicles, pedestrians, and traffic signals. Despite advancements …

3D Object DetectionAutonomous DrivingObjectobject-detection+2

On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning

2026-06-21 · Zihui Zhao, Yuanbo Tang, Yang Li arxiv

Dictionary learning has long been studied from both optimization and probabilistic perspectives. While formulations with element-wise sparsity regularization (e.g., L1-based sparse coding) admit well-established probabil…

EM-NeSy: Expectation Maximization for Neurosymbolic Learning

2026-06-12 · Annegret Seibt, Luc De Raedt, Giuseppe Marra arxiv

Neurosymbolic (NeSy) models integrate neural networks and symbolic reasoning for robust and interpretable AI. State-of-the-art NeSy models require that the symbolic component is expressed in a differentiable way, often c…

Computational Efficiency