Related papers: IoUCert: Robustness Verification for Anchor-based …

360{\deg} cameras have gained popularity over the last few years. In this paper, we propose two fundamental techniques -- Field-of-View IoU (FoV-IoU) and 360Augmentation for object detection in 360{\deg} images. Although most object…

Practical object detection application can lose its effectiveness on image inputs with natural distribution shifts. This problem leads the research community to pay more attention on the robustness of detectors under Out-Of-Distribution…

Unbiased confidence estimates of neural networks are crucial especially for safety-critical applications. Many methods have been developed to calibrate biased confidence estimates. Though there is a variety of methods for classification,…

Detecting and tracking vehicles in urban scenes is a crucial step in many traffic-related applications as it helps to improve road user safety among other benefits. Various challenges remain unresolved in multi-object tracking (MOT)…

Underwater object detection (UOD) remains a critical challenge in computer vision due to underwater distortions which degrade low-level features and compromise the reliability of even state-of-the-art detectors. While YOLO models have…

Arbitrary-oriented object detection (AOOD) is a challenging task to detect objects in the wild with arbitrary orientations and cluttered arrangements. Existing approaches are mainly based on anchor-based boxes or dense points, which rely on…

In object detection, the intersection over union (IoU) threshold is frequently used to define positives/negatives. The threshold used to train a detector defines its \textit{quality}. While the commonly used threshold of 0.5 leads to noisy…

Keypoint detection underpins many vision tasks, including pose estimation, viewpoint recovery, and 3D reconstruction, yet modern neural models remain vulnerable to small input perturbations. Despite its importance, formal robustness…

Object encoding and identification are crucial for many robotic tasks such as autonomous exploration and semantic relocalization. Existing works heavily rely on the tracking of detected objects but have difficulty recalling revisited…

The availability of real-world datasets is the prerequisite for developing object detection methods for autonomous driving. While ambiguity exists in object labels due to error-prone annotation process or sensor observation noises, current…

Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection. Noting that most state-of-the-art object detectors benefit from fine-tuning a…

Modern oriented object detectors typically predict a set of bounding boxes and select the top-ranked ones based on estimated localization quality. Achieving high detection performance requires that the estimated quality closely aligns with…

Anchor-based Siamese trackers have achieved remarkable advancements in accuracy, yet the further improvement is restricted by the lagged tracking robustness. We find the underlying reason is that the regression network in anchor-based…

Robustness is a fundamental aspect for developing safe and trustworthy models, particularly when they are deployed in the open world. In this work we analyze the inherent capability of one-stage object detectors to robustly operate in the…

Transformer-based object detectors (DETR) have shown significant performance across machine vision tasks, ultimately in object detection. This detector is based on a self-attention mechanism along with the transformer encoder-decoder…

An important paradigm in 3D object detection is the use of multiple modalities to enhance accuracy in both normal and challenging conditions, particularly for long-tail scenarios. To address this, recent studies have explored two directions…

We propose an algorithm to enhance certified robustness of a deep model ensemble by optimally weighting each base model. Unlike previous works on using ensembles to empirically improve robustness, our algorithm is based on optimizing a…

Machine learning has demonstrated remarkable performance over finite datasets, yet whether the scores over the fixed benchmarks can sufficiently indicate the model's performance in the real world is still in discussion. In reality, an ideal…

In this paper, we propose a general approach to optimize anchor boxes for object detection. Nowadays, anchor boxes are widely adopted in state-of-the-art detection frameworks. However, these frameworks usually pre-define anchor box shapes…

As self-driving technology advances toward widespread adoption, determining safe operational thresholds across varying environmental conditions becomes critical for public safety. This paper proposes a method for evaluating the robustness…