EZSR: Event-based Zero-Shot Recognition

• URL: http://arxiv.org/abs/2407.21616v2
• Date: Sun, 24 Nov 2024 23:28:09 GMT
• Title: EZSR: Event-based Zero-Shot Recognition
• Authors: Yan Yang, Liyuan Pan, Dongxu Li, Liu Liu,
• Abstract summary: This paper studies zero-shot object recognition using event camera data. We develop an event encoder without relying on additional reconstruction networks. Our model with a ViT/B-16 backbone achieves 47.84% zero-shot accuracy on the N-ImageNet dataset.
• Score: 21.10165234725309
• License:
• Abstract: This paper studies zero-shot object recognition using event camera data. Guided by CLIP, which is pre-trained on RGB images, existing approaches achieve zero-shot object recognition by optimizing embedding similarities between event data and RGB images respectively encoded by an event encoder and the CLIP image encoder. Alternatively, several methods learn RGB frame reconstructions from event data for the CLIP image encoder. However, they often result in suboptimal zero-shot performance. This study develops an event encoder without relying on additional reconstruction networks. We theoretically analyze the performance bottlenecks of previous approaches: the embedding optimization objectives are prone to suffer from the spatial sparsity of event data, causing semantic misalignments between the learned event embedding space and the CLIP text embedding space. To mitigate the issue, we explore a scalar-wise modulation strategy. Furthermore, to scale up the number of events and RGB data pairs for training, we also study a pipeline for synthesizing event data from static RGB images in mass. Experimentally, we demonstrate an attractive scaling property in the number of parameters and synthesized data. We achieve superior zero-shot object recognition performance on extensive standard benchmark datasets, even compared with past supervised learning approaches. For example, our model with a ViT/B-16 backbone achieves 47.84% zero-shot accuracy on the N-ImageNet dataset.

Related papers

• Diffusion-based RGB-D Semantic Segmentation with Deformable Attention Transformer [10.982521876026281]
  We introduce a diffusion-based framework to address the RGB-D semantic segmentation problem. We demonstrate that utilizing a Deformable Attention Transformer as the encoder to extract features from depth images effectively captures the characteristics of invalid regions in depth measurements.
  arXiv  Detail & Related papers  (2024-09-23T15:23:01Z)
• Evaluating Image-Based Face and Eye Tracking with Event Cameras [9.677797822200965]
  Event Cameras, also known as Neuromorphic sensors, capture changes in local light intensity at the pixel level, producing asynchronously generated data termed events'' This data format mitigates common issues observed in conventional cameras, like under-sampling when capturing fast-moving objects. We evaluate the viability of integrating conventional algorithms with event-based data, transformed into a frame format.
  arXiv  Detail & Related papers  (2024-08-19T20:27:08Z)
• Depth-Guided Semi-Supervised Instance Segmentation [62.80063539262021]
  Semi-Supervised Instance (SSIS) aims to leverage an amount of unlabeled data during training. Previous frameworks primarily utilized the RGB information of unlabeled images to generate pseudo-labels. We introduce a Depth-Guided (DG) framework to overcome this limitation.
  arXiv  Detail & Related papers  (2024-06-25T09:36:50Z)
• RGB-Sonar Tracking Benchmark and Spatial Cross-Attention Transformer Tracker [4.235252053339947]
  This paper introduces a new challenging RGB-Sonar (RGB-S) tracking task. It investigates how to achieve efficient tracking of an underwater target through the interaction of RGB and sonar modalities.
  arXiv  Detail & Related papers  (2024-06-11T12:01:11Z)
• Segment Any Events via Weighted Adaptation of Pivotal Tokens [85.39087004253163]
  This paper focuses on the nuanced challenge of tailoring the Segment Anything Models (SAMs) for integration with event data. We introduce a multi-scale feature distillation methodology to optimize the alignment of token embeddings originating from event data with their RGB image counterparts.
  arXiv  Detail & Related papers  (2023-12-24T12:47:08Z)
• Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection [22.60228799622782]
  Key bottleneck in object detection in IR images is lack of sufficient labeled training data. We seek to leverage cues from the RGB modality to scale object detectors to the IR modality, while preserving model performance in the RGB modality. We first pretrain these factor matrices on the RGB modality, for which plenty of training data are assumed to exist and then augment only a few trainable parameters for training on the IR modality to avoid over-fitting.
  arXiv  Detail & Related papers  (2023-09-28T16:55:52Z)
• Chasing Day and Night: Towards Robust and Efficient All-Day Object Detection Guided by an Event Camera [8.673063170884591]
  EOLO is a novel object detection framework that achieves robust and efficient all-day detection by fusing both RGB and event modalities. Our EOLO framework is built based on a lightweight spiking neural network (SNN) to efficiently leverage the asynchronous property of events.
  arXiv  Detail & Related papers  (2023-09-17T15:14:01Z)
• EventTransAct: A video transformer-based framework for Event-camera based action recognition [52.537021302246664]
  Event cameras offer new opportunities compared to standard action recognition in RGB videos. In this study, we employ a computationally efficient model, namely the video transformer network (VTN), which initially acquires spatial embeddings per event-frame. In order to better adopt the VTN for the sparse and fine-grained nature of event data, we design Event-Contrastive Loss ($mathcalL_EC$) and event-specific augmentations.
  arXiv  Detail & Related papers  (2023-08-25T23:51:07Z)
• Beyond Learned Metadata-based Raw Image Reconstruction [86.1667769209103]
  Raw images have distinct advantages over sRGB images, e.g., linearity and fine-grained quantization levels. They are not widely adopted by general users due to their substantial storage requirements. We propose a novel framework that learns a compact representation in the latent space, serving as metadata.
  arXiv  Detail & Related papers  (2023-06-21T06:59:07Z)
• Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images [89.81919625224103]
  Training deep models for RGB-D salient object detection (SOD) often requires a large number of labeled RGB-D images. We present a Dual-Semi RGB-D Salient Object Detection Network (DS-Net) to leverage unlabeled RGB images for boosting RGB-D saliency detection.
  arXiv  Detail & Related papers  (2022-01-01T03:02:27Z)
• Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision [76.41657124981549]
  This paper presents a joint learning model for image alignment and RAW-to-sRGB mapping. Experiments show that our method performs favorably against state-of-the-arts on ZRR and SR-RAW datasets.
  arXiv  Detail & Related papers  (2021-08-18T12:41:36Z)

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.