A Denoising Convolutional Neural Network for Self-Supervised Rank Effectiveness Estimation on Image Retrieval

Autor(es)

Valem, Lucas Pascotti ; Guimaraes Pedronette, Daniel Carlos ; ACM

• Tipo de documento: Artigo Científico
• Fonte: PROCEEDINGS OF THE 2021 INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL (ICMR '21); v. N/A, p. 9-pg., 2021-01-01.

Resumo

Image and multimedia retrieval has established as a prominent task in an increasingly digital and visual world. Mainly supported by decades of development on hand-crafted features and the success of deep learning techniques, various different feature extraction and retrieval approaches are currently available. However, the frequent requirements for large training sets still remain as a fundamental bottleneck, especially in real-world and large-scale scenarios. In the scarcity or absence of labeled data, choosing what retrieval approach to use became a central challenge. A promising strategy consists in to estimate the effectiveness of ranked lists without requiring any groundtruth data. Most of the existing measures exploit statistical analysis of the ranked lists and measure the reciprocity among lists of images in the top positions. This work innovates by proposing a new and self-supervised method for this task, the Deep Rank Noise Estimator (DRNE). An algorithm is presented for generating synthetic ranked list data, which is modeled as images and provided for training a Convolutional Neural Network that we propose for effectiveness estimation. The proposed model is a variant of the DnCNN (Denoiser CNN), which intends to interpret the incorrectness of a ranked list as noise, which is learned by the network. Our approach was evaluated on 5 public image datasets and different tasks, including general image retrieval and person re-ID. We also exploited and evaluated the complementary between the proposed approach and related rank-based approaches through fusion strategies. The experimental results showed that the proposed method is capable of achieving up to 0.88 of Pearson correlation with MAP measure in general retrieval scenarios and 0.74 in person re-ID scenarios. (AU)

• Processo FAPESP: 18/15597-6 - Aplicação e investigação de métodos de aprendizado não-supervisionado em tarefas de recuperação e classificação
• Beneficiário: Daniel Carlos Guimarães Pedronette
• Modalidade de apoio: Auxílio à Pesquisa - Jovens Pesquisadores - Fase 2
• Processo FAPESP: 17/25908-6 - Aprendizado fracamente supervisionado para análise de vídeos no domínio comprimido em tarefas de recuperação e classificação para alertas visuais
• Beneficiário: João Paulo Papa
• Modalidade de apoio: Auxílio à Pesquisa - Parceria para Inovação Tecnológica - PITE
• Processo FAPESP: 20/11366-0 - Suporte para ambiente computacional e execução de experimentos: aprendizado fracamente supervisionado e fusão de métodos de classificação
• Beneficiário: Lucas Pascotti Valem
• Modalidade de apoio: Bolsas no Brasil - Programa Capacitação - Treinamento Técnico