Related papers: From COCO to COCO-FP: A Deep Dive into Background …
Object detection, a pivotal task in computer vision, is frequently hindered by dataset imbalances, particularly the under-explored issue of foreground-foreground class imbalance. This lack of attention to foreground-foreground class…
The Common Objects in Context (COCO) dataset has been instrumental in benchmarking object detectors over the past decade. Like every dataset, COCO contains subtle errors and imperfections stemming from its annotation procedure. With the…
In this paper, we analyze failure cases of state-of-the-art detectors and observe that most hard false positives result from classification instead of localization and they have a large negative impact on the performance of object…
In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely \textbf{slender objects}. In real-world scenarios, slender objects are actually very common and crucial to the objective…
The success of large pre-trained object detectors hinges on their adaptability to diverse downstream tasks. While fine-tuning is the standard adaptation method, specializing these models for challenging fine-grained domains necessitates…
The detection of small objects is a challenging task in computer vision. Conventional object detection methods have difficulty in finding the balance between high detection and low false alarm rates. In the literature, some methods have…
Object detection is a very important function of visual perception systems. Since the early days of classical object detection based on HOG to modern deep learning based detectors, object detection has improved in accuracy. Two stage…
Object detection remains as one of the most notorious open problems in computer vision. Despite large strides in accuracy in recent years, modern object detectors have started to saturate on popular benchmarks raising the question of how…
Object detection remains as one of the most notorious open problems in computer vision. Despite large strides in accuracy in recent years, modern object detectors have started to saturate on popular benchmarks raising the question of how…
The accuracy of state-of-the-art Faster R-CNN and YOLO object detectors are evaluated and compared on a special masked MS COCO dataset to measure how much their predictions rely on contextual information encoded at object category level.…
Current state-of-the-art object detection algorithms still suffer the problem of imbalanced distribution of training data over object classes and background. Recent work introduced a new loss function called focal loss to mitigate this…
As autonomous vehicles and autonomous racing rise in popularity, so does the need for faster and more accurate detectors. While our naked eyes are able to extract contextual information almost instantly, even from far away, image resolution…
In this paper, we study the problem of object counting with incomplete annotations. Based on the observation that in many object counting problems the target objects are normally repeated and highly similar to each other, we are…
The recent COCO object detection dataset presents several new challenges for object detection. In particular, it contains objects at a broad range of scales, less prototypical images, and requires more precise localization. To address these…
Object detection has gained great progress driven by the development of deep learning. Compared with a widely studied task -- classification, generally speaking, object detection even need one or two orders of magnitude more FLOPs (floating…
The recently presented COCO detection challenge will most probably be the reference benchmark in object detection in the next years. COCO is two orders of magnitude larger than Pascal and has four times the number of categories; so in all…
Object detection, a crucial aspect of computer vision, has seen significant advancements in accuracy and robustness. Despite these advancements, practical applications still face notable challenges, primarily the inaccurate detection or…
Although state-of-the-art object detection methods have shown compelling performance, models often are not robust to adversarial attacks and out-of-distribution data. We introduce a new dataset, Natural Adversarial Objects (NAO), to…
Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures are vulnerable to adversarial attacks (FFF, UAP): low…
Evaluating the COCO mean average precision (MaP) and COCO recall metrics as part of the static computation graph of modern deep learning frameworks poses a unique set of challenges. These challenges include the need for maintaining a…