4 citations · 11 across the 10 of their papers we have counts for
9 papers · 1 filter
Unsupervised and semi-supervised co-salient object detection via segmentation frequency statistics
Souradeep Chakraborty, Shujon Naha, Muhammet Bastan +2
In this paper, we address the detection of co-occurring salient objects (CoSOD) in an image group using frequency statistics in an unsupervised manner, which further enable us to d…
ProcSim: Proxy-based Confidence for Robust Similarity Learning
Oriol Barbany, Xiaofan Lin, Muhammet Bastan +1
Deep Metric Learning (DML) methods aim at learning an embedding space in which distances are closely related to the inherent semantic similarity of the inputs. Previous studies hav…
Hierarchical Proxy-based Loss for Deep Metric Learning
Zhibo Yang, Muhammet Bastan, Xinliang Zhu +2
Proxy-based metric learning losses are superior to pair-based losses due to their fast convergence and low training complexity. However, existing proxy-based losses focus on learni…
T-VSE: Transformer-Based Visual Semantic Embedding
Muhammet Bastan, Arnau Ramisa, Mehmet Tek
Transformer models have recently achieved impressive performance on NLP tasks, owing to new algorithms for self-supervised pre-training on very large text corpora. In contrast, rec…
Semantic Granularity Metric Learning for Visual Search
Dipu Manandhar, Muhammet Bastan, Kim-Hui Yap
Deep metric learning applied to various applications has shown promising results in identification, retrieval and recognition. Existing methods often do not consider different gran…
Large Scale Open-Set Deep Logo Detection
Muhammet Bastan, Hao-Yu Wu, Tian Cao +2
We present an open-set logo detection (OSLD) system, which can detect (localize and recognize) any number of unseen logo classes without re-training; it only requires a small set o…
Remote Detection of Idling Cars Using Infrared Imaging and Deep Networks
Muhammet Bastan, Kim-Hui Yap, Lap-Pui Chau
Idling vehicles waste energy and pollute the environment through exhaust emission. In some countries, idling a vehicle for more than a predefined duration is prohibited and automat…
Active Canny: Edge Detection and Recovery with Open Active Contour Models
Muhammet Bastan, S. Saqib Bukhari, Thomas M. Breuel
We introduce an edge detection and recovery framework based on open active contour models (snakelets). This is motivated by the noisy or broken edges output by standard edge detect…
Multi-View Product Image Search Using Deep ConvNets Representations
Muhammet Bastan, Ozgur Yilmaz
Multi-view product image queries can improve retrieval performance over single view queries significantly. In this paper, we investigated the performance of deep convolutional neur…