SIGMA

--- language: - en pipeline_tag: video-classification --- # Official PyTorch Implementation of SIGMA(ECCV 2024). Paper link : https://arxiv.org/html/2407.15447v1 on Huggingface : https://huggingface.co/papers/2407.15447  ### 🔥 Sinkhorn-Guided Masked Video Modeling Video-based pretraining offers immense potential for learning strong visual representations on an unprecedented scale. Recently, masked video modeling methods have shown promising scalability, yet fall short in capturing higher-level semantics due to reconstructing predefined low-level targets such as pixels. To tackle this, we present Sinkhorn-guided Masked Video Modelling (SIGMA), a novel video pretraining method that jointly learns the video model in addition to a target feature space using a projection network. However, this simple modification means that the regular L2 reconstruction loss will lead to trivial solutions as both networks are jointly optimized. As a solution, we distribute features of space-time tubes evenly across a limited number of learnable clusters. By posing this as an optimal transport problem, we enforce high entropy in the generated features across the batch, infusing semantic and temporal meaning into the feature space. The resulting cluster assignments are used as targets for a symmetric prediction task where the video model predicts cluster assignment of the projection network and vice versa. Experimental results on ten datasets across three benchmarks validate the effectiveness of SIGMA in learning more performant, temporally-aware, and robust video representations improving upon state-of-the-art methods. <!-- ### ⚡️ A Simple, Efficient and Strong Baseline in SSVP VideoMAE uses the simple masked autoencoder and **plain ViT** backbone to perform video self-supervised learning. Due to the extremely high masking ratio, the pre-training time of VideoMAE is **much shorter** than contrastive learning methods (**3.2x** speedup). VideoMAE can serve as **a simple but strong baseline** for future research in self-supervised video pre-training. ### 😮 High performance, but NO extra data required VideoMAE works well for video datasets of different scales and can achieve **87.4%** on Kinects-400, **75.4%** on Something-Something V2, **91.3%** on UCF101, and **62.6%** on HMDB51. To our best knowledge, VideoMAE is the **first** to achi...

Source context: 0 downloads · 3 likes · Pipeline video-classification · Repo SMSD75/SIGMA