2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition

• URL: http://arxiv.org/abs/2012.14950v1
• Date: Tue, 29 Dec 2020 21:40:38 GMT
• Title: 2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition
• Authors: Hengduo Li, Zuxuan Wu, Abhinav Shrivastava, Larry S. Davis
• Abstract summary: We introduce Ada3D, a conditional computation framework that learns instance-specific 3D usage policies to determine frames and convolution layers to be used in a 3D network. We demonstrate that our method achieves similar accuracies to state-of-the-art 3D models while requiring 20%-50% less computation across different datasets.
• Score: 84.697097472401
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D convolutional networks are prevalent for video recognition. While achieving excellent recognition performance on standard benchmarks, they operate on a sequence of frames with 3D convolutions and thus are computationally demanding. Exploiting large variations among different videos, we introduce Ada3D, a conditional computation framework that learns instance-specific 3D usage policies to determine frames and convolution layers to be used in a 3D network. These policies are derived with a two-head lightweight selection network conditioned on each input video clip. Then, only frames and convolutions that are selected by the selection network are used in the 3D model to generate predictions. The selection network is optimized with policy gradient methods to maximize a reward that encourages making correct predictions with limited computation. We conduct experiments on three video recognition benchmarks and demonstrate that our method achieves similar accuracies to state-of-the-art 3D models while requiring 20%-50% less computation across different datasets. We also show that learned policies are transferable and Ada3D is compatible to different backbones and modern clip selection approaches. Our qualitative analysis indicates that our method allocates fewer 3D convolutions and frames for "static" inputs, yet uses more for motion-intensive clips.

Related papers

• EmbodiedSAM: Online Segment Any 3D Thing in Real Time [61.2321497708998]
  Embodied tasks require the agent to fully understand 3D scenes simultaneously with its exploration. An online, real-time, fine-grained and highly-generalized 3D perception model is desperately needed.
  arXiv  Detail & Related papers  (2024-08-21T17:57:06Z)
• OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding [54.981605111365056]
  This paper introduces OpenGaussian, a method based on 3D Gaussian Splatting (3DGS) capable of 3D point-level open vocabulary understanding. Our primary motivation stems from observing that existing 3DGS-based open vocabulary methods mainly focus on 2D pixel-level parsing.
  arXiv  Detail & Related papers  (2024-06-04T07:42:33Z)
• AutoDecoding Latent 3D Diffusion Models [95.7279510847827]
  We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space. We then identify the appropriate intermediate volumetric latent space, and introduce robust normalization and de-normalization operations.
  arXiv  Detail & Related papers  (2023-07-07T17:59:14Z)
• Optimization Planning for 3D ConvNets [123.43419144051703]
  It is not trivial to optimally learn a 3D Convolutional Neural Networks (3D ConvNets) due to high complexity and various options of the training scheme. We decompose the path into a series of training "states" and specify the hyper- parameters, e.g., learning rate and the length of input clips, in each state. We perform dynamic programming over all the candidate states to plan the optimal permutation of states, i.e., optimization path.
  arXiv  Detail & Related papers  (2022-01-11T16:13:31Z)
• Learnable Sampling 3D Convolution for Video Enhancement and Action Recognition [24.220358793070965]
  We introduce a new module to improve the capability of 3D convolution (emphLS3D-Conv) We add learnable 2D offsets to 3D convolution which aims to sample locations on spatial feature maps across frames. The experiments on video, video super-resolution, video denoising, and action recognition demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-11-22T09:20:49Z)
• Learning to Predict the 3D Layout of a Scene [0.3867363075280544]
  We propose a method that only uses a single RGB image, thus enabling applications in devices or vehicles that do not have LiDAR sensors. We use the KITTI dataset for training, which consists of street traffic scenes with class labels, 2D bounding boxes and 3D annotations with seven degrees of freedom. We achieve a mean average precision of 47.3% for moderately difficult data, measured at a 3D intersection over union threshold of 70%, as required by the official KITTI benchmark; outperforming previous state-of-the-art single RGB only methods by a large margin.
  arXiv  Detail & Related papers  (2020-11-19T17:23:30Z)
• Making a Case for 3D Convolutions for Object Segmentation in Videos [16.167397418720483]
  We show that 3D convolutional networks can be effectively applied to dense video prediction tasks such as salient object segmentation. We propose a 3D decoder architecture, that comprises novel 3D Global Convolution layers and 3D Refinement modules. Our approach outperforms existing state-of-the-arts by a large margin on the DAVIS'16 Unsupervised, FBMS and ViSal benchmarks.
  arXiv  Detail & Related papers  (2020-08-26T12:24:23Z)
• A Real-time Action Representation with Temporal Encoding and Deep Compression [115.3739774920845]
  We propose a new real-time convolutional architecture, called Temporal Convolutional 3D Network (T-C3D), for action representation. T-C3D learns video action representations in a hierarchical multi-granularity manner while obtaining a high process speed. Our method achieves clear improvements on UCF101 action recognition benchmark against state-of-the-art real-time methods by 5.4% in terms of accuracy and 2 times faster in terms of inference speed with a less than 5MB storage model.
  arXiv  Detail & Related papers  (2020-06-17T06:30:43Z)

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.