Search Results for author: Emre Akbas

Found 28 papers, 24 papers with code

MoCap-to-Visual Domain Adaptation for Efficient Human Mesh Estimation from 2D Keypoints

no code implementations10 Apr 2024 Bedirhan Uguz, Ozhan Suat, Batuhan Karagoz, Emre Akbas

Crucially, our DA method does not require 3D labels for visual data, which enables adaptation to target sets without the need for costly labels.

Domain Adaptation

RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses

1 code implementation CVPR 2024 Bedrettin Cetinkaya, Sinan Kalkan, Emre Akbas

Detecting edges in images suffers from the problems of (P1) heavy imbalance between positive and negative classes as well as (P2) label uncertainty owing to disagreement between different annotators.

Edge Detection

WAIT: Feature Warping for Animation to Illustration video Translation using GANs

1 code implementation7 Oct 2023 Samet Hicsonmez, Nermin Samet, Fidan Samet, Oguz Bakir, Emre Akbas, Pinar Duygulu

Current state-of-the-art video-to-video translation models rely on having a video sequence or a single style image to stylize an input video.

Image-to-Image Translation Optical Flow Estimation +3

Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art

1 code implementation10 Sep 2023 Aref Miri Rekavandi, Shima Rashidi, Farid Boussaid, Stephen Hoefs, Emre Akbas, Mohammed Bennamoun

Transformers have rapidly gained popularity in computer vision, especially in the field of object recognition and detection.

Object object-detection +2

Improving Sketch Colorization using Adversarial Segmentation Consistency

1 code implementation20 Jan 2023 Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu

We leverage semantic image segmentation from a general-purpose panoptic segmentation network to generate an additional adversarial loss function.

Colorization Image Segmentation +4

Correlation Loss: Enforcing Correlation between Classification and Localization

1 code implementation3 Jan 2023 Fehmi Kahraman, Kemal Oksuz, Sinan Kalkan, Emre Akbas

(ii) Motivated by our observations, e. g., that NMS-free detectors can also benefit from correlation, we propose Correlation Loss, a novel plug-in loss function that improves the performance of various object detectors by directly optimizing correlation coefficients: E. g., Correlation Loss on Sparse R-CNN, an NMS-free method, yields 1. 6 AP gain on COCO and 1. 8 AP gain on Cityscapes dataset.

Classification Inductive Bias +1

Character Generation through Self-Supervised Vectorization

no code implementations3 Aug 2022 Gokcen Gokceoglu, Emre Akbas

As a result, it produces a final raster image by drawing the strokes on a canvas, using a minimal number of strokes and dynamically deciding when to stop.

Image Generation

Representation Recycling for Streaming Video Analysis

1 code implementation28 Apr 2022 Can Ufuk Ertenli, Ramazan Gokberk Cinbis, Emre Akbas

Our experiments on video semantic segmentation, video object detection, and human pose estimation in videos show that StreamDEQ achieves on-par accuracy with the baseline while being more than 2-4x faster.

object-detection Pose Estimation +3

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 +2

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 Segmentation +1

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 +3

HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation

1 code implementation8 Jun 2021 Nermin Samet, Emre Akbas

Differently, in whole-body pose estimation, the locations of fine-grained keypoints (68 on face, 21 on each hand and 3 on each foot) are estimated as well, which creates a scale variance problem that needs to be addressed.

2D Human Pose Estimation Face Detection +6

HoughNet: Integrating near and long-range evidence for visual detection

3 code implementations14 Apr 2021 Nermin Samet, Samet Hicsonmez, Emre Akbas

This paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method.

3D Object Detection Image Generation +6

A Deeper Look into Convolutions via Eigenvalue-based Pruning

1 code implementation4 Feb 2021 Ilke Cugu, Emre Akbas

Convolutional neural networks (CNNs) are able to attain better visual recognition performance than fully connected neural networks despite having much fewer parameters due to their parameter sharing principle.

Image Classification

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

2 code implementations21 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 +6

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

3 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 +2

HoughNet: Integrating near and long-range evidence for bottom-up object detection

2 code implementations ECCV 2020 Nermin Samet, Samet Hicsonmez, Emre Akbas

We further validate the effectiveness of our proposal in another task, namely, "labels to photo" image generation by integrating the voting module of HoughNet to two different GAN models and showing that the accuracy is significantly improved in both cases.

Image Generation Object +2

GANILLA: Generative Adversarial Networks for Image to Illustration Translation

4 code implementations13 Feb 2020 Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu

To address this problem, we propose a new framework for the quantitative evaluation of image-to-illustration models, where both content and style are taken into account using separate classifiers.

Image-to-Image Translation Translation

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 object-detection +1

MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network

4 code implementations ECCV 2018 Muhammed Kocabas, Salih Karagoz, Emre Akbas

In this paper, we present MultiPoseNet, a novel bottom-up multi-person pose estimation architecture that combines a multi-task model with a novel assignment method.

Human Detection Keypoint Detection +1

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 object-detection +1

Supervised Infinite Feature Selection

1 code implementation9 Apr 2017 Sadegh Eskandari, Emre Akbas

In this paper, we present a new feature selection method that is suitable for both unsupervised and supervised problems.

feature selection General Classification +1

Object Detection Through Exploration With A Foveated Visual Field

1 code implementation4 Aug 2014 Emre Akbas, Miguel P. Eckstein

Similar to the human visual system, the FOD has higher resolution at the fovea and lower resolution at the visual periphery.

Object object-detection +1

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