{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-to-segment-object-candidates-via","title":"Learning to Segment Object Candidates via Recursive Neural Networks","arxiv_id":"1612.01057","date":"2016-12-04","proceeding":null,"authors":["Tianshui Chen","Liang Lin","Xian Wu","Nong Xiao","Xiaonan Luo"],"abstract":"To avoid the exhaustive search over locations and scales, current\nstate-of-the-art object detection systems usually involve a crucial component\ngenerating a batch of candidate object proposals from images. In this paper, we\npresent a simple yet effective approach for segmenting object proposals via a\ndeep architecture of recursive neural networks (ReNNs), which hierarchically\ngroups regions for detecting object candidates over scales. Unlike traditional\nmethods that mainly adopt fixed similarity measures for merging regions or\nfinding object proposals, our approach adaptively learns the region merging\nsimilarity and the objectness measure during the process of hierarchical region\ngrouping. Specifically, guided by a structured loss, the ReNN model jointly\noptimizes the cross-region similarity metric with the region merging process as\nwell as the objectness prediction. During inference of the object proposal\ngeneration, we introduce randomness into the greedy search to cope with the\nambiguity of grouping regions. Extensive experiments on standard benchmarks,\ne.g., PASCAL VOC and ImageNet, suggest that our approach is capable of\nproducing object proposals with high recall while well preserving the object\nboundaries and outperforms other existing methods in both accuracy and\nefficiency.","url_abs":"http://arxiv.org/abs/1612.01057v4","url_pdf":"http://arxiv.org/pdf/1612.01057v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-proposal-generation","task_name":"Object Proposal Generation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"deepmask","method_name":"DeepMask"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"deepmask","name":"DeepMask","full_name":"DeepMask"}],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}