Exploiting CLIP for Zero-shot HOI Detection Requires Knowledge Distillation at Multiple Levels

• URL: http://arxiv.org/abs/2309.05069v1
• Date: Sun, 10 Sep 2023 16:27:54 GMT
• Title: Exploiting CLIP for Zero-shot HOI Detection Requires Knowledge Distillation at Multiple Levels
• Authors: Bo Wan and Tinne Tuytelaars
• Abstract summary: We employ CLIP, a large-scale pre-trained vision-language model, for knowledge distillation on multiple levels. To train our model, CLIP is utilized to generate HOI scores for both global images and local union regions. The model achieves strong performance, which is even comparable with some fully-supervised and weakly-supervised methods.
• Score: 52.50670006414656
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we investigate the task of zero-shot human-object interaction (HOI) detection, a novel paradigm for identifying HOIs without the need for task-specific annotations. To address this challenging task, we employ CLIP, a large-scale pre-trained vision-language model (VLM), for knowledge distillation on multiple levels. Specifically, we design a multi-branch neural network that leverages CLIP for learning HOI representations at various levels, including global images, local union regions encompassing human-object pairs, and individual instances of humans or objects. To train our model, CLIP is utilized to generate HOI scores for both global images and local union regions that serve as supervision signals. The extensive experiments demonstrate the effectiveness of our novel multi-level CLIP knowledge integration strategy. Notably, the model achieves strong performance, which is even comparable with some fully-supervised and weakly-supervised methods on the public HICO-DET benchmark.

Related papers

• Simple Image-level Classification Improves Open-vocabulary Object Detection [27.131298903486474]
  Open-Vocabulary Object Detection (OVOD) aims to detect novel objects beyond a given set of base categories on which the detection model is trained. Recent OVOD methods focus on adapting the image-level pre-trained vision-language models (VLMs), such as CLIP, to a region-level object detection task via, eg., region-level knowledge distillation, regional prompt learning, or region-text pre-training. These methods have demonstrated remarkable performance in recognizing regional visual concepts, but they are weak in exploiting the VLMs' powerful global scene understanding ability learned from the billion-scale
  arXiv  Detail & Related papers  (2023-12-16T13:06:15Z)
• Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models [55.20626448358655]
  This study explores the universal interaction recognition in an open-world setting through the use of Vision-Language (VL) foundation models and large language models (LLMs) Our design includes an HO Prompt-guided Decoder (HOPD), facilitates the association of high-level relation representations in the foundation model with various HO pairs within the image. For open-category interaction recognition, our method supports either of two input types: interaction phrase or interpretive sentence.
  arXiv  Detail & Related papers  (2023-11-07T08:27:32Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• Exploring Open-Vocabulary Semantic Segmentation without Human Labels [76.15862573035565]
  We present ZeroSeg, a novel method that leverages the existing pretrained vision-language model (VL) to train semantic segmentation models. ZeroSeg overcomes this by distilling the visual concepts learned by VL models into a set of segment tokens, each summarizing a localized region of the target image. Our approach achieves state-of-the-art performance when compared to other zero-shot segmentation methods under the same training data.
  arXiv  Detail & Related papers  (2023-06-01T08:47:06Z)
• HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models [30.279621764192843]
  Human-Object Interaction (HOI) detection aims to localize human-object pairs and recognize their interactions. Contrastive Language-Image Pre-training (CLIP) has shown great potential in providing interaction prior for HOI detectors. We propose a novel HOI detection framework that efficiently extracts prior knowledge from CLIP and achieves better generalization.
  arXiv  Detail & Related papers  (2023-03-28T07:54:54Z)
• From MNIST to ImageNet and Back: Benchmarking Continual Curriculum Learning [9.104068727716294]
  Continual learning (CL) is one of the most promising trends in machine learning research. We introduce two novel CL benchmarks that involve multiple heterogeneous tasks from six image datasets. We additionally structure our benchmarks so that tasks are presented in increasing and decreasing order of complexity.
  arXiv  Detail & Related papers  (2023-03-16T18:11:19Z)
• Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning [66.00600682711995]
  Human object interaction (HOI) detection plays a crucial role in human-centric scene understanding and serves as a fundamental building-block for many vision tasks. One generalizable and scalable strategy for HOI detection is to use weak supervision, learning from image-level annotations only. This is inherently challenging due to ambiguous human-object associations, large search space of detecting HOIs and highly noisy training signal. We develop a CLIP-guided HOI representation capable of incorporating the prior knowledge at both image level and HOI instance level, and adopt a self-taught mechanism to prune incorrect human-object associations.
  arXiv  Detail & Related papers  (2023-03-02T14:41:31Z)
• Learning to Discover and Detect Objects [43.52208526783969]
  We tackle the problem of novel class discovery, detection, and localization (NCDL) In this setting, we assume a source dataset with labels for objects of commonly observed classes. By training our detection network with this objective in an end-to-end manner, it learns to classify all region proposals for a large variety of classes.
  arXiv  Detail & Related papers  (2022-10-19T17:59:55Z)
• UniT: Unified Knowledge Transfer for Any-shot Object Detection and Segmentation [52.487469544343305]
  Methods for object detection and segmentation rely on large scale instance-level annotations for training. We propose an intuitive and unified semi-supervised model that is applicable to a range of supervision.
  arXiv  Detail & Related papers  (2020-06-12T22:45:47Z)

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.