Evolving Losses for Unsupervised Video Representation Learning

By A. Piergiovanni, Anelia Angelova, Michael S. Ryoo. 2020

149 citations recorded by the source corpus.

We present a new method to learn video representations from large-scale unlabeled video data. Ideally, this representation will be generic and transferable, directly usable for new tasks such as action recognition and zero or few-shot learning. We formulate unsupervised representation learning as a multi-modal, multi-task learning problem, where the representations are shared across different modalities via distillation. Further, we introduce the concept of loss function evolution by using an evolutionary search algorithm to automatically find optimal combination of loss functions capturing many (self-supervised) tasks and modalities. Thirdly, we propose an unsupervised representation evaluation metric using distribution matching to a large unlabeled dataset as a prior constraint, based on Zipf's law. This unsupervised constraint, which is not guided by any labeling, produces similar results to weakly-supervised, task-specific ones. The proposed unsupervised representation learning results in a single RGB network and outperforms previous methods. Notably, it is also more effective than several label-based methods (e.g., ImageNet), with the exception of large, fully labeled video datasets.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Self-Supervised MultiModal Versatile Networks (2020, methodology): “Recent developments such as XDC [7], who employ cross-modality clustering, or Evolving Losses [67], where m any single- and multi-modal pretext tasks are used, demonstrate an impressive ability to learn good representations in both modalities.”
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text (2021, background): “Multimodal self-supervised learning can be achieved by predicting whether a video has correspondence with an audio stream [4, 5, 68, 54], cross-modality clustering [3], and evolving losses [73].”
Self-supervised Co-training for Video Representation Learning (2020, unknown): “0 ELO [50] 2020 Youtube8M- (8y) 224 R(2+1)D 65 V+A 3 – 64.”
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training (2022, background): “[52] AJ Piergiovanni, Anelia Angelova, and Michael S Ryoo.”
What Should Not Be Contrastive in Contrastive Learning (2020, background): “This phenomenon becomes more obvious in multi-task self-supervised learning [7, 36, 29, 28, 1] as the optimization goal for each task can be very different depending on the pretext task.”
A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, methodology): “reinforcement learning [107], Bayesian inference [108] and evolutionary algorithms [109] in an attempt to automatically find optimization strategies through heuristic algorithms.”
A Survey on Self-Supervised Learning: Algorithms, Applications, and Future Trends (2023, methodology): “It has been combined with clustering [66], semi-supervised learning [151], multi-task learning [163]–[166], transfer learning [167]–[169], graph NNs [153], [170]–[175], reinforcement learning [176]–[178], few-shot learning [179], [180], neural”
Self-Supervised Learning by Cross-Modal Audio-Video Clustering (2019, methodology): “0 ELo [50] R(2+1)D-50 YouTube-8M 93.”
A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning (2021, methodology): “Unsupervised learning in videos has followed a similar trajectory with earlier methods focusing on predictive tasks based on motion, color and spatiotemporal ordering [29,43,1, 44,78,85,60,84,58,57,21,51,86,66,22,48,91,16,87,70,45], and contrastive objectives with visual [74, 79, 34, 53, 28, 92] and”
Parameter Efficient Multimodal Transformers for Video Representation Learning (2020, background): “…leverage unlabeled videos from speciﬁc domains (Owens et al., 2016; Gao & Grauman, 2019; Zhao et al., 2018; Ephrat et al., 2018; Alwassel et al., 2019; Miech et al., 2020; Piergiovanni et al., 2020) and often demonstrate on audio-visual source separation, localization, and co-segmentation.”