Multi-utility Learning: Structured-output Learning with Multiple Annotation-specific Loss Functions

2014-06-23 · Roman Shapovalov, Dmitry Vetrov, Anton Osokin, Pushmeet Kohli

Structured-output learning is a challenging problem; particularly so because of the difficulty in obtaining large datasets of fully labelled instances for training. In this paper we try to overcome this difficulty by presenting a multi-utility learning framework for structured prediction that can learn from training instances with different forms of supervision. We propose a unified technique for inferring the loss functions most suitable for quantifying the consistency of solutions with the given weak annotation. We demonstrate the effectiveness of our framework on the challenging semantic image segmentation problem for which a wide variety of annotations can be used. For instance, the popular training datasets for semantic segmentation are composed of images with hard-to-generate full pixel labellings, as well as images with easy-to-obtain weak annotations, such as bounding boxes around objects, or image-level labels that specify which object categories are present in an image. Experimental evaluation shows that the use of annotation-specific loss functions dramatically improves segmentation accuracy compared to the baseline system where only one type of weak annotation is used.

📄 PDF Abstract BibTeX arXiv:1406.5910

Code (0)

등록된 구현이 없습니다.

Tasks

Image Segmentation Segmentation Semantic Segmentation Structured Prediction

Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations

2018-06-08 · ICML 2018 7 · Ashwin Kalyan, Stefan Lee, Anitha Kannan, Dhruv Batra

Many structured prediction problems (particularly in vision and language domains) are ambiguous, with multiple outputs being correct for an input - e.g. there are many ways of describing an image, multiple ways of transl…

Diversity Multi-Label Classification MUlTI-LABEL-ClASSIFICATION Question Generation+3

ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling

2025-10-16 · Jianghao Lin, Yuanyuan Shi, Xin Peng, Renjie Ding 외 arxiv

Large language models (LLMs) excel at function calling, but inference scaling has been explored mainly for unstructured generation. We propose an inference-scaling framework for structured outputs that combines fine-grai…

Domain Adaptation for Structured Output via Discriminative Patch Representations

2019-01-16 · ICCV 2019 10 · Yi-Hsuan Tsai, Kihyuk Sohn, Samuel Schulter, Manmohan Chandraker

Predicting structured outputs such as semantic segmentation relies on expensive per-pixel annotations to learn supervised models like convolutional neural networks. However, models trained on one data domain may not gene…

Domain Adaptation Image-to-Image Translation Segmentation Semantic Segmentation+1

Best of Both Worlds: Human-Machine Collaboration for Object Annotation

2015-06-01 · CVPR 2015 6 · Olga Russakovsky, Li-Jia Li, Li Fei-Fei

The long-standing goal of localizing every object in an image remains elusive. Manually annotating objects is quite expensive despite crowd engineering innovations. Current state-of-the-art automatic object detectors can…

Object object-detection Object Detection

Organizing Unstructured Image Collections using Natural Language

2024-10-07 · Mingxuan Liu, Zhun Zhong, Jun Li, Gianni Franchi 외

Organizing unstructured visual data into semantic clusters is a key challenge in computer vision. Traditional deep clustering (DC) approaches focus on a single partition of data, while multiple clustering (MC) methods ad…

Clustering Deep Clustering