Search Results for author: Sinan Kalkan

Found 21 papers, 12 papers with code

Does depth estimation help object detection?

no code implementations13 Apr 2022 Bedrettin Cetinkaya, Sinan Kalkan, Emre Akbas

Ground-truth depth, when combined with color data, helps improve object detection accuracy over baseline models that only use color.

Depth Estimation Object Detection

Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation

1 code implementation19 Oct 2021 Kemal Oksuz, Baris Can Cam, Fehmi Kahraman, Zeynep Sonat Baltaci, Sinan Kalkan, Emre Akbas

We present the effectiveness of maIoU on a state-of-the-art (SOTA) assigner, ATSS, by replacing IoU operation by our maIoU and training YOLACT, a SOTA real-time instance segmentation method.

Real-time Instance Segmentation Semantic Segmentation

Rank & Sort Loss for Object Detection and Instance Segmentation

3 code implementations ICCV 2021 Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan

RS Loss supervises the classifier, a sub-network of these methods, to rank each positive above all negatives as well as to sort positives among themselves with respect to (wrt.)

Instance Segmentation Object Detection +1

One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks

1 code implementation21 Nov 2020 Kemal Oksuz, Baris Can Cam, Sinan Kalkan, Emre Akbas

Despite being widely used as a performance measure for visual detection tasks, Average Precision (AP) is limited in (i) reflecting localisation quality, (ii) interpretability and (iii) robustness to the design choices regarding its computation, and its applicability to outputs without confidence scores.

Instance Segmentation Keypoint Detection +3

Spatio-Temporal Analysis of Facial Actions using Lifecycle-Aware Capsule Networks

no code implementations17 Nov 2020 Nikhil Churamani, Sinan Kalkan, Hatice Gunes

In real-world interactions, however, facial expressions are usually more subtle and evolve in a temporal manner requiring AU detection models to learn spatial as well as temporal information.

Frame

Transformer-Encoder Detector Module: Using Context to Improve Robustness to Adversarial Attacks on Object Detection

no code implementations13 Nov 2020 Faisal Alamri, Sinan Kalkan, Nicolas Pugeault

Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures are vulnerable to adversarial attacks (FFF, UAP): low amplitude perturbations, barely perceptible by the human eye, can lead to a drastic reduction in labeling performance.

Object Detection Object Recognition

A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection

2 code implementations NeurIPS 2020 Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan

We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection.

Classification General Classification +1

Investigating Bias and Fairness in Facial Expression Recognition

no code implementations20 Jul 2020 Tian Xu, Jennifer White, Sinan Kalkan, Hatice Gunes

Recognition of expressions of emotions and affect from facial images is a well-studied research problem in the fields of affective computing and computer vision with a large number of datasets available containing facial images and corresponding expression labels.

Data Augmentation Facial Expression Recognition +1

ALET (Automated Labeling of Equipment and Tools): A Dataset, a Baseline and a Usecase for Tool Detection in the Wild

1 code implementation25 Oct 2019 Fatih Can Kurnaz, Burak Hocaoğlu, Mert Kaan Yılmaz, İdil Sülo, Sinan Kalkan

Robots collaborating with humans in realistic environments will need to be able to detect the tools that can be used and manipulated.

Object Detection

Generating Positive Bounding Boxes for Balanced Training of Object Detectors

1 code implementation21 Sep 2019 Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan

Using our generator as an analysis tool, we show that (i) IoU imbalance has an adverse effect on performance, (ii) hard positive example mining improves the performance only for certain input IoU distributions, and (iii) the imbalance among the foreground classes has an adverse effect on performance and that it can be alleviated at the batch level.

Object Detection

Imbalance Problems in Object Detection: A Review

1 code implementation31 Aug 2019 Kemal Oksuz, Baris Can Cam, Sinan Kalkan, Emre Akbas

In this paper, we present a comprehensive review of the imbalance problems in object detection.

Object Detection

Searching for Ambiguous Objects in Videos using Relational Referring Expressions

1 code implementation3 Aug 2019 Hazan Anayurt, Sezai Artun Ozyegin, Ulfet Cetin, Utku Aktas, Sinan Kalkan

Especially in ambiguous settings, humans prefer expressions (called relational referring expressions) that describe an object with respect to a distinguishing, unique object.

Deep Attention Natural Language Visual Grounding +1

Learning to Generate Unambiguous Spatial Referring Expressions for Real-World Environments

no code implementations15 Apr 2019 Fethiye Irmak Doğan, Sinan Kalkan, Iolanda Leite

Referring to objects in a natural and unambiguous manner is crucial for effective human-robot interaction.

Referring Expression

Localization Recall Precision (LRP): A New Performance Metric for Object Detection

3 code implementations ECCV 2018 Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan

Moreover, we present LRP results of a simple online video object detector which uses a SOTA still image object detector and show that the class-specific optimized thresholds increase the accuracy against the common approach of using a general threshold for all classes.

Object Detection

COSMO: Contextualized Scene Modeling with Boltzmann Machines

1 code implementation2 Jul 2018 Ilker Bozcan, Sinan Kalkan

For this end, we introduce a hybrid version of BMs where relations and affordances are introduced with shared, tri-way connections into the model.

Object Detection

A Deep Incremental Boltzmann Machine for Modeling Context in Robots

no code implementations13 Oct 2017 Fethiye Irmak Doğan, Hande Çelikkanat, Sinan Kalkan

Context is an essential capability for robots that are to be as adaptive as possible in challenging environments.

General Classification Scene Classification

Using Deep Networks for Drone Detection

no code implementations18 Jun 2017 Cemal Aker, Sinan Kalkan

Drone detection is the problem of finding the smallest rectangle that encloses the drone(s) in a video sequence.

Object Detection

A Large-scale Dataset and Benchmark for Similar Trademark Retrieval

2 code implementations20 Jan 2017 Osman Tursun, Cemal Aker, Sinan Kalkan

In this paper, we provide a large-scale dataset with benchmark queries with which different TR approaches can be evaluated systematically.

Trademark Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.