|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Time-series of satellite images may reveal important data about changes in environmental conditions and natural or urban landscape structures that are of potential interest to citizens, historians, or policymakers.
In 16 bits, our log float multiply-add is 0. 59x the power and 0. 68x the area of IEEE 754 float16 fused multiply-add, maintaining the same signficand precision and dynamic range, proving useful for training ASICs as well.
Armed with this knowledge, we quantize the model parameters, activations and layer gradients to 8-bit, leaving at a higher precision only the final step in the computation of the weight gradients.
The weights in the other group are responsible to compensate for the accuracy loss from the quantization, thus they are the ones to be re-trained.
In this paper, we propose a new unsupervised deep learning approach called DeepBit to learn compact binary descriptor for efficient visual object matching.