paper-with-me

Papers

Robust Learning Through Cross-Task Consistency

2020-06-07 · Amir Zamir, Alexander Sax, Teresa Yeo, Oğuzhan Kar, Nikhil Cheerla, Rohan Suri, Zhangjie Cao, Jitendra Malik, Leonidas Guibas

Visual perception entails solving a wide set of tasks, e.g., object detection, depth estimation, etc. The predictions made for multiple tasks from the same image are not independent, and therefore, are expected to be consistent. We propose a broadly applicable and fully computational method for augmenting learning with Cross-Task Consistency. The proposed formulation is based on inference-path invariance over a graph of arbitrary tasks. We observe that learning with cross-task consistency leads to more accurate predictions and better generalization to out-of-distribution inputs. This framework also leads to an informative unsupervised quantity, called Consistency Energy, based on measuring the intrinsic consistency of the system. Consistency Energy correlates well with the supervised error (r=0.67), thus it can be employed as an unsupervised confidence metric as well as for detection of out-of-distribution inputs (ROC-AUC=0.95). The evaluations are performed on multiple datasets, including Taskonomy, Replica, CocoDoom, and ApolloScape, and they benchmark cross-task consistency versus various baselines including conventional multi-task learning, cycle consistency, and analytical consistency.

📄 PDF Abstract BibTeX arXiv:2006.04096

Code (1)

EPFL-VILAB/XTConsistency 공식 구현 pytorch

Tasks

3D ReconstructionDepth EstimationMulti-Task Learningobject-detectionObject DetectionSurface Normals Estimation

Similar Papers 제목 키워드 기반

Robust Learning Through Cross-Task Consistency

2020-06-01 · CVPR 2020 6 · Amir R. Zamir, Alexander Sax, Nikhil Cheerla, Rohan Suri 외

Visual perception entails solving a wide set of tasks (e.g., object detection, depth estimation, etc). The predictions made for different tasks out of one image are not independent, and therefore, are expected to be 'con…

3D ReconstructionDepth EstimationMonocular Depth Estimationobject-detection+3

TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency

2022-10-11 · Dan Zhang, Rui Zheng, Luosang Gadeng, Pei Yang

This paper addresses the task of semantic segmentation in computer vision, aiming to achieve precise pixel-wise classification. We investigate the joint training of models for semantic edge detection and semantic segment…

Autonomous DrivingEdge DetectionMulti-Task LearningReal-Time Semantic Segmentation+2

Batched Self-Consistency Improves LLM Relevance Assessment and Ranking

2025-05-18 · Anton Korikov, Pan Du, Scott Sanner, Navid Rekabsaz

Given some information need, Large Language Models (LLMs) are increasingly used for candidate text relevance assessment, typically using a one-by-one pointwise (PW) strategy where each LLM call evaluates one candidate at…

Passage Retrieval

On the Entity-Level Alignment in Crosslingual Consistency

2025-10-11 · Yihong Liu, Mingyang Wang, François Yvon, Hinrich Schütze arxiv

Multilingual large language models (LLMs) are expected to recall factual knowledge consistently across languages. However, the factors that give rise to such crosslingual consistency -- and its frequent failure -- remain…

Entity Alignment

Socrates-Mol: Self-Oriented Cognitive Reasoning through Autonomous Trial-and-Error with Empirical-Bayesian Screening for Molecules

2025-11-14 · Xiangru Wang, Zekun Jiang, Heng Yang, Cheng Tan 외 arxiv

Molecular property prediction is fundamental to chemical engineering applications such as solvent screening. We present Socrates-Mol, a framework that transforms language models into empirical Bayesian reasoners through …

Molecular Property Prediction