Search
Results
-
The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures
(2021)2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)In this paper, we tackle the problem of convolutional neural network design. Instead of focusing on the design of the overall architecture, we investigate a design space that is usually overlooked, i.e. adjusting the channel configurations of predefined networks. We find that this adjustment can be achieved by shrinking widened baseline networks and leads to superior performance. Based on that, we articulate the "heterogeneity hypothesis": ...Conference Paper -
The Ninth Visual Object Tracking VOT2021 Challenge Results
(2021)2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative. Results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years. The VOT2021 challenge was composed of four sub-challenges focusing on different tracking domains: (i) VOT-ST2021 challenge focused on short-term tracking in RGB, ...Conference Paper -
Arbitrary-Scale Image Synthesis
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Positional encodings have enabled recent works to train a single adversarial network that can generate images of different scales. However, these approaches are either limited to a set of discrete scales or struggle to maintain good perceptual quality at the scales for which the model is not trained explicitly. We propose the design of scale-consistent positional encodings invariant to our generator's layers transformations. This enables ...Conference Paper -
Generating Masks from Boxes by Mining Spatio-Temporal Consistencies in Videos
(2021)2021 IEEE/CVF International Conference on Computer Vision (ICCV)Segmenting objects in videos is a fundamental computer vision task. The current deep learning based paradigm offers a powerful, but data-hungry solution. However, current datasets are limited by the cost and human effort of annotating object masks in videos. This effectively limits the performance and generalization capabilities of existing video segmentation methods. To address this issue, we explore weaker form of bounding box annotations.We ...Conference Paper -
Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU
(2021)2021 IEEE/CVF International Conference on Computer Vision (ICCV)The state-of-the-art object detection and image classification methods can perform impressively on more than 9k classes. In contrast, the number of classes in semantic segmentation datasets is relatively limited. This is not surprising when the restrictions caused by the lack of labeled data and high computation demand for segmentation are considered. In this paper, we propose a novel training methodology to train and scale the existing ...Conference Paper -
Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
(2021)2021 IEEE/CVF International Conference on Computer Vision (ICCV)Normalizing flows have recently demonstrated promising results for low-level vision tasks. For image super-resolution (SR), it learns to predict diverse photo-realistic high-resolution (HR) images from the low-resolution (LR) image rather than learning a deterministic mapping. For image rescaling, it achieves high accuracy by jointly modelling the downscaling and upscaling processes. While existing approaches employ specialized techniques ...Conference Paper -
Learning Target Candidate Association To Keep Track of What Not To Track
(2021)2021 IEEE/CVF International Conference on Computer Vision (ICCV)The presence of objects that are confusingly similar to the tracked target, poses a fundamental challenge in appearance-based visual tracking. Such distractor objects are easily misclassified as the target itself, leading to eventual tracking failure. While most methods strive to suppress distractors through more powerful appearance models, we take an alternative approach.We propose to keep track of distractor objects in order to continue ...Conference Paper -
Transforming Model Prediction for Tracking
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Optimization based tracking methods have been widely successful by integrating a target model prediction module, providing effective global reasoning by minimizing an objective function. While this inductive bias integrates valuable domain knowledge, it limits the expressivity of the tracking network. In this work, we therefore propose a tracker architecture employing a Transformer-based model prediction module. Transformers capture global ...Conference Paper -
Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolution
(2022)2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)Super-resolution is an ill-posed problem, where a ground-truth high-resolution image represents only one possibility in the space of plausible solutions. Yet, the dominant paradigm is to employ pixel-wise losses, such as L-1, which drive the prediction towards a blurry average. This leads to fundamentally conflicting objectives when combined with adversarial losses, which degrades the final quality. We address this issue by revisiting the ...Conference Paper -
Fast Few-Shot Classification by Few-Iteration Meta-Learning
(2021)2021 IEEE International Conference on Robotics and Automation (ICRA)Conference Paper