Related papers: FLOAT: Factorized Learning of Object Attributes fo…
Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This…
Deep learning-based object detection and instance segmentation have achieved unprecedented progress. In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and…
Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency.…
Effective fusion of different types of features is the key to salient object detection. The majority of existing network structure design is based on the subjective experience of scholars and the process of feature fusion does not consider…
Vision-based 3D Semantic Scene Completion (SSC) has received growing attention due to its potential in autonomous driving. While most existing approaches follow an ego-centric paradigm by aggregating and diffusing features over the entire…
Despite recent advancements in computer vision research, object detection in aerial images still suffers from several challenges. One primary challenge to be mitigated is the presence of multiple types of variation in aerial images, for…
General-purpose object-detection algorithms often dismiss the fine structure of detected objects. This can be traced back to how their proposed regions are evaluated. Our goal is to renegotiate the trade-off between the generality of these…
Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…
A key algorithm for understanding the world is material segmentation, which assigns a label (metal, glass, etc.) to each pixel. We find that a model trained on existing data underperforms in some settings and propose to address this with a…
Despite the remarkable progress, weakly supervised segmentation approaches are still inferior to their fully supervised counterparts. We obverse the performance gap mainly comes from their limitation on learning to produce high-quality…
Segmenting semantic objects from images and parsing them into their respective semantic parts are fundamental steps towards detailed object understanding in computer vision. In this paper, we propose a joint solution that tackles semantic…
Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…
Video object segmentation (VOS) aims at segmenting a particular object throughout the entire video clip sequence. The state-of-the-art VOS methods have achieved excellent performance (e.g., 90+% J&F) on existing datasets. However, since the…
Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for…
The aim of fine-grained recognition is to identify sub-ordinate categories in images like different species of birds. Existing works have confirmed that, in order to capture the subtle differences across the categories, automatic…
Humans tend to mine objects by learning from a group of images or several frames of video since we live in a dynamic world. In the computer vision area, many researches focus on co-segmentation (CoS), co-saliency detection (CoSD) and video…
As the number of installed cameras grows, so do the compute resources required to process and analyze all the images captured by these cameras. Video analytics enables new use cases, such as smart cities or autonomous driving. At the same…
Despite significant advances in generic object detection, a persistent performance gap remains for tiny objects compared to normal-scale objects. We demonstrate that tiny objects are highly sensitive to annotation noise, where optimizing…
Deep learning has enabled remarkable advances in scene understanding, particularly in semantic segmentation tasks. Yet, current state of the art approaches are limited to a closed set of classes, and fail when facing novel elements, also…
Artificial Intelligence (AI)-driven defect inspection is pivotal in industrial manufacturing. Yet, many methods, tailored to specific pipelines, grapple with diverse product portfolios and evolving processes. Addressing this, we present the…