Related papers: Enhancing Your Trained DETRs with Box Refinement

Dynamic Optimization Problems (DOPs) are challenging to address due to their complex nature, i.e., dynamic environment variation. Evolutionary Computation methods are generally advantaged in solving DOPs since they resemble dynamic…

While humans can successfully navigate using abstractions, ignoring details that are irrelevant to the task at hand, most existing robotic applications require the maintenance of a detailed environment representation which consumes a…

Object detection is a central downstream task used to test if pre-trained network parameters confer benefits, such as improved accuracy or training speed. The complexity of object detection methods can make this benchmarking non-trivial…

The conventional, widely used treatment of deep learning models as black boxes provides limited or no insights into the mechanisms that guide neural network decisions. Significant research effort has been dedicated to building interpretable…

Detection of arbitrarily rotated objects is a challenging task due to the difficulties of locating the multi-angle objects and separating them effectively from the background. The existing methods are not robust to angle varies of the…

With the success of deep learning techniques in a broad range of application domains, many deep learning software frameworks have been developed and are being updated frequently to adapt to new hardware features and software libraries,…

Recent self-supervised methods are mainly designed for representation learning with the base model, e.g., ResNets or ViTs. They cannot be easily transferred to DETR, with task-specific Transformer modules. In this work, we present Siamese…

Although existing neural retrieval models reveal promising results when training data is abundant and the performance keeps improving as training data increases, collecting high-quality annotated data is prohibitively costly. To this end,…

We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate, leading to training…

One of the bottlenecks for instance segmentation today lies in the conflicting requirements of high-resolution inputs and lightweight, real-time inference. To address this bottleneck, we present a Polygon Detection Transformer (Poly-DETR)…

In this paper, we explore a principal way to enhance the quality of object masks produced by different segmentation models. We propose a model-agnostic solution called SegRefiner, which offers a novel perspective on this problem by…

Deep equilibrium networks (DEQs) are a new class of models that eschews traditional depth in favor of finding the fixed point of a single nonlinear layer. These models have been shown to achieve performance competitive with the…

Recently, Transformer-based methods, which predict polygon points or Bezier curve control points for localizing texts, are popular in scene text detection. However, these methods built upon detection transformer framework might achieve…

Several low-bandwidth distributable black-box optimization algorithms in the family of finite differences such as Evolution Strategies have recently been shown to perform nearly as well as tailored Reinforcement Learning methods in some…

We present a novel method for efficiently producing semi-dense matches across images. Previous detector-free matcher LoFTR has shown remarkable matching capability in handling large-viewpoint change and texture-poor scenarios but suffers…

Deep neural networks can capture the intricate interaction history information between queries and documents, because of their many complicated nonlinear units, allowing them to provide correct search recommendations. However, service…

Image relighting has emerged as a problem of significant research interest inspired by augmented reality applications. Physics-based traditional methods, as well as black box deep learning models, have been developed. The existing deep…

In the field of deep learning based computer vision, the development of deep object detection has led to unique paradigms (e.g., two-stage or set-based) and architectures (e.g., Faster-RCNN or DETR) which enable outstanding performance on…

We propose a novel approach for instance-level image retrieval. It produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors. In contrast to previous works employing pre-trained…

The tasks of object detection and trajectory forecasting play a crucial role in understanding the scene for autonomous driving. These tasks are typically executed in a cascading manner, making them prone to compounding errors. Furthermore,…