The speed-accuracy Pareto curve of object detection systems have advanced through a combination of better model architectures, training and inference methods. In this paper, we methodically evaluate a variety of these techniques to understand where most of the improvements in modern detection systems come from. We benchmark these improvements on the vanilla ResNet-FPN backbone with RetinaNet and RCNN detectors. The vanilla detectors are improved by 7.7% in accuracy while being 30% faster in speed. We further provide simple scaling strategies to generate family of models that form two Pareto curves, named RetinaNet-RS and Cascade RCNN-RS. These simple rescaled detectors explore the speed-accuracy trade-off between the one-stage RetinaNet detectors and two-stage RCNN detectors. Our largest Cascade RCNN-RS models achieve 52.9% AP with a ResNet152-FPN backbone and 53.6% with a SpineNet143L backbone. Finally, we show the ResNet architecture, with three minor architectural changes, outperforms EfficientNet as the backbone for object detection and instance segmentation systems.
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Microsoft Research（微软研究院）
PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks such as PointMLP and Point Transformer, we find that a large portion of the performance gain is due to improved training strategies, i.e. data augmentation and optimization techniques, and increased model sizes rather than architectural innovations. Thus, the full potential of PointNet++ has yet to be explored. In this work, we revisit the classical PointNet++ through a systematic study of model training and scaling stra…
Contrastive learning has emerged as a competitive pretraining method for object detection. Despite this progress, there has been minimal investigation into the robustness of contrastively pretrained detectors when faced with domain shifts. To address this gap, we conduct an empirical study of contrastive learning and out-of-domain object detection, studying how contrastive view design affects robustness. In particular, we perform a case study of the detection-focused pretext task Instance Localization (InsLoc) and propose strategies to augment views and enhance robustness in appearance-shifted…
In this paper we focus on improving object detection performance in terms of recall. We propose a post-detection stage during which we explore the image with the objective of recovering missed detections. This exploration is performed by sampling object proposals in the image. We analyze four different strategies to perform this sampling, giving special attention to strategies that exploit spatial relations between objects. In addition, we propose a novel method to discover higher-order relations between groups of objects. Experiments on the challenging KITTI dataset show that our proposed rel…
Semantic image segmentation aims to obtain object labels with precise boundaries, which usually suffers from overfitting. Recently, various data augmentation strategies like regional dropout and mix strategies have been proposed to address the problem. These strategies have proved to be effective for guiding the model to attend on less discriminative parts. However, current strategies operate at the image level, and objects and the background are coupled. Thus, the boundaries are not well augmented due to the fixed semantic scenario. In this paper, we propose ObjectAug to perform object-level …
Queensland University of Technology（昆士兰科技大学）；ARC Centre of Excellence for Robotic Vision（澳大利亚研究理事会机器人视觉卓越中心）
There has been a recent emergence of sampling-based techniques for estimating epistemic uncertainty in deep neural networks. While these methods can be applied to classification or semantic segmentation tasks by simply averaging samples, this is not the case for object detection, where detection sample bounding boxes must be accurately associated and merged. A weak merging strategy can significantly degrade the performance of the detector and yield an unreliable uncertainty measure. This paper provides the first in-depth investigation of the effect of different association and merging strategi…
In vision-enabled autonomous systems such as robots and autonomous cars, video object detection plays a crucial role, and both its speed and accuracy are important factors to provide reliable operation. The key insight we show in this paper is that speed and accuracy are not necessarily a trade-off when it comes to image scaling. Our results show that re-scaling the image to a lower resolution will sometimes produce better accuracy. Based on this observation, we propose a novel approach, dubbed AdaScale, which adaptively selects the input image scale that improves both accuracy and speed for v…
University of São Paulo（圣保罗大学）；Eldorado Research Institute（埃尔多拉多研究所）
The field of Continual Learning investigates the ability to learn consecutive tasks without losing performance on those previously learned. Its focus has been mainly on incremental classification tasks. We believe that research in continual object detection deserves even more attention due to its vast range of applications in robotics and autonomous vehicles. This scenario is more complex than conventional classification given the occurrence of instances of classes that are unknown at the time, but can appear in subsequent tasks as a new class to be learned, resulting in missing annotations an…
Novel computer vision architectures monopolize the spotlight, but the impact of the model architecture is often conflated with simultaneous changes to training methodology and scaling strategies. Our work revisits the canonical ResNet (He et al., 2015) and studies these three aspects in an effort to disentangle them. Perhaps surprisingly, we find that training and scaling strategies may matter more than architectural changes, and further, that the resulting ResNets match recent state-of-the-art models. We show that the best performing scaling strategy depends on the training regime and offer t…
In this work we analyze strategies for convolutional neural network scaling; that is, the process of scaling a base convolutional network to endow it with greater computational complexity and consequently representational power. Example scaling strategies may include increasing model width, depth, resolution, etc. While various scaling strategies exist, their tradeoffs are not fully understood. Existing analysis typically focuses on the interplay of accuracy and flops (floating point operations). Yet, as we demonstrate, various scaling strategies affect model parameters, activations, and conse…
Brown University（布朗大学）；Artificial and Natural Intelligence Toulouse Institute (ANITI)（图卢兹人工智能与自然智能研究所（ANITI））；Carney Institute for Brain Science（卡尼脑科学研究所）
The many successes of deep neural networks (DNNs) over the past decade have largely been driven by computational scale rather than insights from biological intelligence. Here, we explore if these trends have also carried concomitant improvements in explaining the visual strategies humans rely on for object recognition. We do this by comparing two related but distinct properties of visual strategies in humans and DNNs: where they believe important visual features are in images and how they use those features to categorize objects. Across 84 different DNNs trained on ImageNet and three independe…
A recent work from Bello shows that training and scaling strategies may be more significant than model architectures for visual recognition. This short note studies effective training and scaling strategies for video recognition models. We propose a simple scaling strategy for 3D ResNets, in combination with improved training strategies and minor architectural changes. The resulting models, termed 3D ResNet-RS, attain competitive performance of 81.0 on Kinetics-400 and 83.8 on Kinetics-600 without pre-training. When pre-trained on a large Web Video Text dataset, our best model achieves 83.5 an…
Columbia University（哥伦比亚大学）；Allen Institute for AI（艾伦人工智能研究所）
People often use physical intuition when manipulating articulated objects, irrespective of object semantics. Motivated by this observation, we identify an important embodied task where an agent must play with objects to recover their parts. To this end, we introduce Act the Part (AtP) to learn how to interact with articulated objects to discover and segment their pieces. By coupling action selection and motion segmentation, AtP is able to isolate structures to make perceptual part recovery possible without semantic labels. Our experiments show AtP learns efficient strategies for part discovery…
University of Texas at Austin（得克萨斯大学奥斯汀分校）；Houzz, Inc.（Houzz公司）
Crowdsourcing is a valuable approach for tracking objects in videos in a more scalable manner than possible with domain experts. However, existing frameworks do not produce high quality results with non-expert crowdworkers, especially for scenarios where objects split. To address this shortcoming, we introduce a crowdsourcing platform called CrowdMOT, and investigate two micro-task design decisions: (1) whether to decompose the task so that each worker is in charge of annotating all objects in a sub-segment of the video versus annotating a single object across the entire video, and (2) whether…
Beijing University of Posts and Telecommunications（北京邮电大学）
In recent years, algorithms for multiple object tracking tasks have benefited from great progresses in deep models and video quality. However, in challenging scenarios like drone videos, they still suffer from problems, such as small objects, camera movements and view changes. In this paper, we propose a new multiple object tracker, which employs Global Information And some Optimizing strategies, named GIAOTracker. It consists of three stages, i.e., online tracking, global link and post-processing. Given detections in every frame, the first stage generates reliable tracklets using information …
Malek Ashtar University of Technology（马利克·阿什塔尔理工大学）
Object tracking is one of the foremost assignments in computer vision that has numerous commonsense applications such as traffic monitoring, robotics, autonomous vehicle tracking, and so on. Different researches have been tried later a long time, but since of diverse challenges such as occlusion, illumination variations, fast motion, etc. researches in this area continues. In this paper, different strategies of the following objects are inspected and a comprehensive classification is displayed that classified the following strategies into four fundamental categories of feature-based, segmentat…
Jiangnan University（江南大学）；University of Surrey（萨里大学）
We address the problem of multi-modal object tracking in video and explore various options of fusing the complementary information conveyed by the visible (RGB) and thermal infrared (TIR) modalities including pixel-level, feature-level and decision-level fusion. Specifically, different from the existing methods, paradigm of image fusion task is heeded for fusion at pixel level. Feature-level fusion is fulfilled by attention mechanism with channels excited optionally. Besides, at decision level, a novel fusion strategy is put forward since an effortless averaging configuration has shown the sup…
We present the MDS feature learning framework, in which multidimensional scaling (MDS) is applied on high-level pairwise image distances to learn fixed-length vector representations of images. The aspects of the images that are captured by the learned features, which we call MDS features, completely depend on what kind of image distance measurement is employed. With properly selected semantics-sensitive image distances, the MDS features provide rich semantic information about the images that is not captured by other feature extraction techniques. In our work, we introduce the iterated Levenber…
Training on datasets with long-tailed distributions has been challenging for major recognition tasks such as classification and detection. To deal with this challenge, image resampling is typically introduced as a simple but effective approach. However, we observe that long-tailed detection differs from classification since multiple classes may be present in one image. As a result, image resampling alone is not enough to yield a sufficiently balanced distribution at the object level. We address object-level resampling by introducing an object-centric memory replay strategy based on dynamic, ep…
X-ray security screening is in widespread use to maintain transportation security against a wide range of potential threat profiles. Of particular interest is the recent focus on the use of automated screening approaches, including the potential anomaly detection as a methodology for concealment detection within complex electronic items. Here we address this problem considering varying segmentation strategies to enable the use of both object level and sub-component level anomaly detection via the use of secondary convolutional neural network (CNN) architectures. Relative performance is evaluat…
