Evaluating Context for Deep Object Detectors

• URL: http://arxiv.org/abs/2205.02887v1
• Date: Thu, 5 May 2022 18:48:29 GMT
• Title: Evaluating Context for Deep Object Detectors
• Authors: Osman Semih Kayhan and Jan C. van Gemert
• Abstract summary: We group object detectors into 3 categories in terms of context use. We create a fully controlled dataset for varying context. We demonstrate that single-stage and two-stage object detectors can and will use the context by virtue of their large receptive field.
• Score: 18.932504899552494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Which object detector is suitable for your context sensitive task? Deep object detectors exploit scene context for recognition differently. In this paper, we group object detectors into 3 categories in terms of context use: no context by cropping the input (RCNN), partial context by cropping the featuremap (two-stage methods) and full context without any cropping (single-stage methods). We systematically evaluate the effect of context for each deep detector category. We create a fully controlled dataset for varying context and investigate the context for deep detectors. We also evaluate gradually removing the background context and the foreground object on MS COCO. We demonstrate that single-stage and two-stage object detectors can and will use the context by virtue of their large receptive field. Thus, choosing the best object detector may depend on the application context.

Related papers

• ContextHOI: Spatial Context Learning for Human-Object Interaction Detection [24.381821663963898]
  spatial contexts are considered critical in Human-Object Interaction (HOI) recognition. We present a dual-branch framework named ContextHOI, which efficiently captures both object detection features and spatial contexts. ContextHOI achieves state-of-the-art performance on the HICO-DET and v-coco benchmarks.
  arXiv  Detail & Related papers  (2024-12-12T08:21:19Z)
• Improving Object Detection via Local-global Contrastive Learning [27.660633883387753]
  We present a novel image-to-image translation method that specifically targets cross-domain object detection. We learn to represent objects by contrasting local-global information. This affords investigation of an under-explored challenge: obtaining performant detection, under domain shifts.
  arXiv  Detail & Related papers  (2024-10-07T14:18:32Z)
• Context Disentangling and Prototype Inheriting for Robust Visual Grounding [56.63007386345772]
  Visual grounding (VG) aims to locate a specific target in an image based on a given language query. We propose a novel framework with context disentangling and prototype inheriting for robust visual grounding to handle both scenes. Our method outperforms the state-of-the-art methods in both scenarios.
  arXiv  Detail & Related papers  (2023-12-19T09:03:53Z)
• Detecting out-of-context objects using contextual cues [29.92843037720968]
  We propose a graph contextual reasoning network (GCRN) to detect out-of-context (OOC) objects in an image. GCRN consists of two separate graphs to predict object labels based on the contextual cues in the image. GCRN explicitly captures the contextual cues to improve the detection of in-context objects and identify objects that violate contextual relations.
  arXiv  Detail & Related papers  (2022-02-11T23:15:01Z)
• Context-Aware Transfer Attacks for Object Detection [51.65308857232767]
  We present a new approach to generate context-aware attacks for object detectors. We show that by using co-occurrence of objects and their relative locations and sizes as context information, we can successfully generate targeted mis-categorization attacks.
  arXiv  Detail & Related papers  (2021-12-06T18:26:39Z)
• Aligning Pretraining for Detection via Object-Level Contrastive Learning [57.845286545603415]
  Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. We argue that this could be sub-optimal and thus advocate a design principle which encourages alignment between the self-supervised pretext task and the downstream task. Our method, called Selective Object COntrastive learning (SoCo), achieves state-of-the-art results for transfer performance on COCO detection.
  arXiv  Detail & Related papers  (2021-06-04T17:59:52Z)
• Self-supervised object detection from audio-visual correspondence [101.46794879729453]
  We tackle the problem of learning object detectors without supervision. We do not assume image-level class labels, instead we extract a supervisory signal from audio-visual data. We show that our method can learn to detect generic objects that go beyond instruments, such as airplanes and cats.
  arXiv  Detail & Related papers  (2021-04-13T17:59:03Z)
• Learning Object Detection from Captions via Textual Scene Attributes [70.90708863394902]
  We argue that captions contain much richer information about the image, including attributes of objects and their relations. We present a method that uses the attributes in this "textual scene graph" to train object detectors. We empirically demonstrate that the resulting model achieves state-of-the-art results on several challenging object detection datasets.
  arXiv  Detail & Related papers  (2020-09-30T10:59:20Z)
• Robust Object Detection under Occlusion with Context-Aware CompositionalNets [21.303976151518125]
  Compositional convolutional neural networks (CompositionalNets) have been shown to be robust at classifying occluded objects. We propose to overcome two limitations of CompositionalNets which will enable them to detect partially occluded objects.
  arXiv  Detail & Related papers  (2020-05-24T02:57:34Z)
• MLCVNet: Multi-Level Context VoteNet for 3D Object Detection [51.45832752942529]
  We propose Multi-Level Context VoteNet (MLCVNet) to recognize 3D objects correlatively, building on the state-of-the-art VoteNet. We introduce three context modules into the voting and classifying stages of VoteNet to encode contextual information at different levels. Our method is an effective way to promote detection accuracy, achieving new state-of-the-art detection performance on challenging 3D object detection datasets.
  arXiv  Detail & Related papers  (2020-04-12T19:10:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.