Efficient Deep Learning Analytics refers to the optimization of deep learning techniques and models to maximize performance while minimizing computational resources, time, and energy consumption. This involves strategies such as model compression, pruning, quantization, and the use of specialized hardware to ensure that deep learning tasks, such as training and inference, are conducted more effectively and efficiently.

Posts

Deep Video Codec Control for Vision Models

Standardized lossy video coding is at the core of almost all real-world video processing pipelines. Rate control is used to enable standard codecs to adapt to different network bandwidth conditions or storage constraints. However standard video codecs (e.g. H.264) and their rate control modules aim to minimize video distortion w.r.t. human quality assessment. We demonstrate empirically that standard-coded videos vastly deteriorate the performance of deep vision models. To overcome the deterioration of vision performance this paper presents the first end-to-end learnable deep video codec control that considers both bandwidth constraints and downstream deep vision performance while adhering to existing standardization. We demonstrate that our approach better preserves downstream deep vision performance than traditional standard video coding.